diff --git "a/cs772_proj/cs772_project.ipynb" "b/cs772_proj/cs772_project.ipynb"
deleted file mode 100644--- "a/cs772_proj/cs772_project.ipynb"
+++ /dev/null
@@ -1,2294 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": 1,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "M5l56S6sSS86",
-        "outputId": "23a1f317-c555-418a-cfa5-d9042ddfc464"
-      },
-      "outputs": [],
-      "source": [
-        "#!pip install datasets\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 2,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#!pip install urllib3==2.0.7"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 3,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#!pip install python-dateutil==2.8.2"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 4,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#!pip install pytz==2023.4"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 5,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#!pip show datasets"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 6,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#!python -V"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 7,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#!pip install fsspec==2023.6.0"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 8,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#!pip install pandas==2.0.3"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 15,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "m5JyRVPfSZE-",
-        "outputId": "fd48acd6-d5ff-450b-e7aa-1cfee4c2ddd1"
-      },
-      "outputs": [],
-      "source": [
-        "from datasets import load_dataset\n",
-        "\n",
-        "#ds = load_dataset('json' , data_files= data_root + 'dataset.json')\n",
-        "\n",
-        "ds = load_dataset(r\"hatexplain\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 16,
-      "metadata": {
-        "id": "g5-XaBy3Sfpd"
-      },
-      "outputs": [],
-      "source": [
-        "from datasets import load_dataset, DatasetDict\n",
-        "\n",
-        "# Define a function to preprocess the dataset\n",
-        "def preprocess(example):\n",
-        "    # Rename the 'post_tokens' feature to 'text'\n",
-        "    example['text'] = ' '.join(example['post_tokens'])\n",
-        "    example['label'] = max(example['annotators']['label'], key=example['annotators']['label'].count)\n",
-        "    del example['post_tokens']\n",
-        "    del example['rationales']\n",
-        "    return example\n",
-        "\n",
-        "# Apply the preprocessing function to each split of the dataset\n",
-        "dataset = DatasetDict({\n",
-        "    split: ds[split].map(preprocess)\n",
-        "    for split in ds.keys()\n",
-        "})"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 17,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "Js3u0m-ySwEY",
-        "outputId": "7a9ed5ae-fe19-4c79-a285-82385ed4ab0f"
-      },
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "1\n"
-          ]
-        }
-      ],
-      "source": [
-        "hatex_prompt=dataset['train'][15005][\"text\"]\n",
-        "print(dataset['train'][15005][\"label\"])"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 18,
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "<user> you are right do not kill yourself but jesus stop posting this shit\n"
-          ]
-        }
-      ],
-      "source": [
-        "print(hatex_prompt)\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 13,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "SLPWGH4CeaOC",
-        "outputId": "f08474fe-f427-4d5f-a2e5-6a44612367fd"
-      },
-      "outputs": [],
-      "source": [
-        "#!pip install pyvene"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 14,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "tu5Ccf_JekGn",
-        "outputId": "494cdf30-4cdd-4e51-e0e7-7eb511f25777"
-      },
-      "outputs": [],
-      "source": [
-        "#!pip install transformers"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 15,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "AdF0W_LxiUFq",
-        "outputId": "d1f4d110-6ee7-4210-bc2d-958a8045fac8"
-      },
-      "outputs": [],
-      "source": [
-        "#!pip install huggingface_hub"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 16,
-      "metadata": {
-        "id": "Cy9SDFCFyimx"
-      },
-      "outputs": [
-        {
-          "data": {
-            "text/plain": [
-              "'from google.colab import output\\noutput.enable_custom_widget_manager()'"
-            ]
-          },
-          "execution_count": 16,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "'''from google.colab import output\n",
-        "output.enable_custom_widget_manager()'''"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 17,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 17,
-          "referenced_widgets": [
-            "071c7cf6402f4a6181d4b469bde1b3cb",
-            "85c8c1e35cef4d748533c9dddb02896e",
-            "1e5cefa47c0f4818865b5d09ca710cc0",
-            "45be68901a2a4d8fbec05de19c92c324",
-            "849d1b8eef1244e68915e92fcd2b21ce",
-            "6da6c2eb83ea4ba0acd528286ce446c8",
-            "34f422b8c7b34f2d9363f35dd5d6d0ff",
-            "60e7eaa94497433190fc974f18eceb7a",
-            "8454b87258ab47f2afdc3e8d48e82e32",
-            "08c5c590a2b34d72a7a55bfe6fe9dafa",
-            "31516d3aeee84dd88edd9a1959d1def7",
-            "ac1a886161c84d21b47627f5796906a9",
-            "17c0de2c2bf74b2ea14c1e6306accf87",
-            "1c7ded73ed064fe88b072fc1ce59bf5a",
-            "c357088019794100828bce478d88bb36",
-            "d124971d76e645adb551aa5244485b96",
-            "38773bbb85ac406da4ccf19ae1a0a586"
-          ]
-        },
-        "id": "NdVimuUhiTUF",
-        "outputId": "ef2dddc4-6e39-42c5-bf9d-d5ff37bf341a"
-      },
-      "outputs": [
-        {
-          "data": {
-            "application/vnd.jupyter.widget-view+json": {
-              "model_id": "eb2aa0a07cb146dabe3c816041b51545",
-              "version_major": 2,
-              "version_minor": 0
-            },
-            "text/plain": [
-              "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
-        }
-      ],
-      "source": [
-        "from huggingface_hub import notebook_login\n",
-        "notebook_login()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 19,
-      "metadata": {
-        "id": "7rCXAtB0yS9K"
-      },
-      "outputs": [],
-      "source": [
-        "import torch\n",
-        "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
-        "import pyvene as pv"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 20,
-      "metadata": {},
-      "outputs": [
-        {
-          "data": {
-            "text/plain": [
-              "True"
-            ]
-          },
-          "execution_count": 20,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "torch.cuda.is_available()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 13,
-      "metadata": {},
-      "outputs": [
-        {
-          "data": {
-            "text/plain": [
-              "14"
-            ]
-          },
-          "execution_count": 13,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "len(hatex_prompt.split())"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 5,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 586,
-          "referenced_widgets": [
-            "3e18465f9ad1485fa27b63d2b3f98914",
-            "625691ae152e40879829d255ad5c60bc",
-            "7f5572f404bf469b90b06f6f89ea5af4",
-            "0c48b20e1c474468b313c5084963889e",
-            "a875503fde864b18902ec6efa72a756c",
-            "cc901f6a4aab456aa49f71850967d233",
-            "668effd825244964b1f46a23a387ff6d",
-            "8eba3af3e6274b5497c85dcaf9d4f767",
-            "ec3809f996b743cc8c5af1d06ca8a6ad",
-            "5f0246adc4e74fde960262d56a27c3d0",
-            "55b5c659d4ff4784a9bbf3173399b3e0"
-          ]
-        },
-        "id": "ICiFJ6jNlG5n",
-        "outputId": "8574cc53-1f7c-4d42-f938-654d5e250d15"
-      },
-      "outputs": [
-        {
-          "ename": "NameError",
-          "evalue": "name 'torch' is not defined",
-          "output_type": "error",
-          "traceback": [
-            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-            "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-            "Cell \u001b[0;32mIn[5], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[43mtorch\u001b[49m\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mis_available():\n\u001b[1;32m      2\u001b[0m     model_id \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmeta-llama/Llama-2-7b-chat-hf\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m      3\u001b[0m     model \u001b[38;5;241m=\u001b[39m AutoModelForCausalLM\u001b[38;5;241m.\u001b[39mfrom_pretrained(model_id, torch_dtype\u001b[38;5;241m=\u001b[39mtorch\u001b[38;5;241m.\u001b[39mfloat16, device_map\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mauto\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
-            "\u001b[0;31mNameError\u001b[0m: name 'torch' is not defined"
-          ]
-        }
-      ],
-      "source": [
-        "if torch.cuda.is_available():\n",
-        "    model_id = \"meta-llama/Llama-2-7b-chat-hf\"\n",
-        "    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map=\"auto\")\n",
-        "    model.cuda()\n",
-        "    tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
-        "    tokenizer.use_default_system_prompt = False\n",
-        "def chat_with_llama(prompt):\n",
-        "    input_ids = tokenizer.encode(prompt, return_tensors=\"pt\")\n",
-        "    input_ids = input_ids.to('cuda')\n",
-        "    output = model.generate(input_ids, max_length=256, num_beams=4, no_repeat_ngram_size=2)\n",
-        "    response = tokenizer.decode(output[0], skip_special_tokens=True)\n",
-        "    return response\n",
-        "\n",
-        "while True:\n",
-        "    prompt = input(\"You: \")\n",
-        "    response = chat_with_llama(prompt)\n",
-        "    print(\"Llama:\", response)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 141,
-          "referenced_widgets": [
-            "02750c86a66b4524942b36ca673e8441",
-            "8efe2ff3e4d04af59a71f25da5c07f78",
-            "2a73966ed0dc48d78befbd340764cab7",
-            "a133914642d3445bb68ebddbd8fb4af0",
-            "12c7dcf05527489b8e5473fbccfb1afe",
-            "9f00991060be45bf8b2020a438501d1d",
-            "efe880306f44444aa51eb239e7d59b13",
-            "ba1dd1977a88451cae4242c57aeed255",
-            "702c06dda74447a3a36142f7f6dd50d7",
-            "e0b89135d45d4a09a6a7ba00311e9fd7",
-            "d48c867b20b7425f8885ea513d18c9ea"
-          ]
-        },
-        "id": "GVtkPoj4eeKo",
-        "outputId": "c32ed918-58e6-4de7-98bc-d516e78f6d15"
-      },
-      "outputs": [
-        {
-          "name": "stderr",
-          "output_type": "stream",
-          "text": [
-            "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:88: UserWarning: \n",
-            "The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
-            "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n",
-            "You will be able to reuse this secret in all of your notebooks.\n",
-            "Please note that authentication is recommended but still optional to access public models or datasets.\n",
-            "  warnings.warn(\n"
-          ]
-        },
-        {
-          "data": {
-            "application/vnd.jupyter.widget-view+json": {
-              "model_id": "02750c86a66b4524942b36ca673e8441",
-              "version_major": 2,
-              "version_minor": 0
-            },
-            "text/plain": [
-              "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
-            ]
-          },
-          "metadata": {
-            "application/vnd.jupyter.widget-view+json": {
-              "colab": {
-                "custom_widget_manager": {
-                  "url": "https://ssl.gstatic.com/colaboratory-static/widgets/colab-cdn-widget-manager/2b70e893a8ba7c0f/manager.min.js"
-                }
-              }
-            }
-          },
-          "output_type": "display_data"
-        }
-      ],
-      "source": [
-        "# others can download from huggingface and use it directly\n",
-        "import torch\n",
-        "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
-        "import pyvene as pv\n",
-        "\n",
-        "tokenizer = AutoTokenizer.from_pretrained(\"meta-llama/Llama-2-7b-chat-hf\")\n",
-        "model = AutoModelForCausalLM.from_pretrained(\n",
-        "    \"meta-llama/Llama-2-7b-chat-hf\",\n",
-        "    torch_dtype=torch.bfloat16,\n",
-        ").to(\"cuda\")\n",
-        "\n",
-        "pv_model = pv.IntervenableModel.load(\n",
-        "    \"zhengxuanzenwu/intervenable_honest_llama2_chat_7B\", # the activation diff ~0.14MB\n",
-        "    model,\n",
-        ")\n",
-        "#output = model.generate(input_ids, max_length=256, num_beams=4, no_repeat_ngram_size=2)\n",
-        "print(\"llama-2-chat loaded with interventions:\")\n",
-        "q = \"What's a cure for insomnia that always works?\"\n",
-        "prompt = tokenizer(q, return_tensors=\"pt\").to(\"cuda\")\n",
-        "_, iti_response_shared = pv_model.generate(prompt, max_new_tokens=64, do_sample=False,max_length=256, num_beams=4, no_repeat_ngram_size=2)\n",
-        "print(tokenizer.decode(iti_response_shared[0], skip_special_tokens=True))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "##gpt-xl"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 21,
-      "metadata": {
-        "id": "HXVfXZ0kfSPC"
-      },
-      "outputs": [],
-      "source": [
-        "import torch\n",
-        "import pandas as pd\n",
-        "import numpy as np\n",
-        "from pyvene import embed_to_distrib, top_vals, format_token\n",
-        "from pyvene import (\n",
-        "    IntervenableModel,\n",
-        "    VanillaIntervention, Intervention,\n",
-        "    RepresentationConfig,\n",
-        "    IntervenableConfig,\n",
-        "    ConstantSourceIntervention,\n",
-        "    LocalistRepresentationIntervention\n",
-        ")\n",
-        "from pyvene import create_gpt2\n",
-        "\n",
-        "%config InlineBackend.figure_formats = ['svg']\n",
-        "from plotnine import (\n",
-        "    ggplot,\n",
-        "    geom_tile,\n",
-        "    aes,\n",
-        "    facet_wrap,\n",
-        "    theme,\n",
-        "    element_text,\n",
-        "    geom_bar,\n",
-        "    geom_hline,\n",
-        "    scale_y_log10,\n",
-        "    xlab, ylab, ylim,\n",
-        "    scale_y_discrete, scale_y_continuous, ggsave\n",
-        ")\n",
-        "from plotnine.scales import scale_y_reverse, scale_fill_cmap\n",
-        "from tqdm import tqdm\n",
-        "\n",
-        "titles={\n",
-        "    \"block_output\": \"single restored layer in GPT2-XL\",\n",
-        "    \"mlp_activation\": \"center of interval of 2 patched mlp layer\",\n",
-        "    \"attention_output\": \"center of interval of 2 patched attn layer\"\n",
-        "}\n",
-        "\n",
-        "colors={\n",
-        "    \"block_output\": \"Purples\",\n",
-        "    \"mlp_activation\": \"Greens\",\n",
-        "    \"attention_output\": \"Reds\"\n",
-        "} \n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 22,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from transformers import AutoTokenizer\n",
-        "from transformers import AutoModelForSequenceClassification\n",
-        "from torch import nn\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 23,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "def create_bert(cache_dir=None):\n",
-        "    \"\"\"Creates a GPT2 model, config, and tokenizer from the given name and revision\"\"\"\n",
-        "    from transformers import BertConfig\n",
-        "\n",
-        "    config = BertConfig.from_pretrained(\"/home/shambhavi/cs772_proj/bert_base/checkpoint-3848/config.json\")\n",
-        "    tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n",
-        "    gpt = AutoModelForSequenceClassification.from_pretrained(\"/home/shambhavi/cs772_proj/bert_base/checkpoint-3848\", config=config, cache_dir=cache_dir)\n",
-        "    print(\"loaded model\")\n",
-        "    return config, tokenizer, gpt"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 24,
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "loaded model\n"
-          ]
-        }
-      ],
-      "source": [
-        "\n",
-        "device = \"cuda:0\" if torch.cuda.is_available() else \"cpu\"\n",
-        "#config, tokenizer, gpt =  pv.create_llama(name=\"sharpbai/alpaca-7b-merged\")\n",
-        "config, tokenizer, gpt = create_bert()\n",
-        "#config, tokenizer, gpt = create_gpt2(name=\"gpt2-xl\")\n",
-        "\n",
-        "gpt.to(device)\n",
-        "\n",
-        "base = hatex_prompt\n",
-        "inputs = [\n",
-        "    tokenizer(base, return_tensors=\"pt\").to(device),\n",
-        "]\n",
-        "#print(base)\n",
-        "base_token = tokenizer.convert_ids_to_tokens(inputs[0]['input_ids'][0])\n",
-        "res = gpt(**inputs[0])\n",
-        "probabilities = nn.functional.softmax(res[0], dim=-1)\n",
-        "#print(probabilities)\n",
-        "#print(res[0][0][0].item())\n",
-        "#print(res)\n",
-        "#distrib = embed_to_distrib(gpt, res.last_hidden_state, logits=False)\n",
-        "#top_vals(tokenizer, distrib[0][-1], n=20)\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 25,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "\n",
-        "class NoiseIntervention(ConstantSourceIntervention, LocalistRepresentationIntervention):\n",
-        "    def __init__(self, embed_dim, **kwargs):\n",
-        "        super().__init__()\n",
-        "        self.interchange_dim = embed_dim\n",
-        "        rs = np.random.RandomState(1)\n",
-        "        prng = lambda *shape: rs.randn(*shape)\n",
-        "        self.noise = torch.from_numpy(\n",
-        "            prng(1, 4, embed_dim)).to(device)\n",
-        "        self.noise_level = 0.7462981581687927 #0.3462981581687927\n",
-        "\n",
-        "    def forward(self, base, source=None, subspaces=None):\n",
-        "        base[..., : self.interchange_dim] += self.noise * self.noise_level\n",
-        "        return base\n",
-        "\n",
-        "    def __str__(self):\n",
-        "        return f\"NoiseIntervention(embed_dim={self.embed_dim})\"\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 26,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "\n",
-        "\n",
-        "def corrupted_config(model_type):\n",
-        "    config = IntervenableConfig(\n",
-        "        model_type=model_type,\n",
-        "        representations=[\n",
-        "            RepresentationConfig(\n",
-        "                0,              # layer\n",
-        "                \"block_input\",  # intervention type\n",
-        "            ),\n",
-        "        ],\n",
-        "        intervention_types=NoiseIntervention,\n",
-        "    )\n",
-        "    return config\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 31,
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "tensor([[0.0161, 0.9457, 0.0382]], device='cuda:0')\n"
-          ]
-        }
-      ],
-      "source": [
-        "\n",
-        "\n",
-        "base = tokenizer(hatex_prompt, return_tensors=\"pt\").to(device)\n",
-        "config = corrupted_config(type(gpt))\n",
-        "intervenable = IntervenableModel(config, gpt)\n",
-        "_, counterfactual_outputs = intervenable(\n",
-        "    base, unit_locations={\"base\": ([[[0,1,2,3]]])}\n",
-        ")\n",
-        "probabilities = nn.functional.softmax(counterfactual_outputs[0], dim=-1)\n",
-        "print(probabilities)\n",
-        "#distrib = embed_to_distrib(gpt, counterfactual_outputs.last_hidden_state, logits=False)\n",
-        "#top_vals(tokenizer, distrib[0][-1], n=10)\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 27,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "\n",
-        "\n",
-        "def restore_corrupted_with_interval_config(\n",
-        "    layer, stream=\"mlp_activation\", window=5, num_layers=12):\n",
-        "    start = max(0, layer - window // 2)\n",
-        "    end = min(num_layers, layer - (-window // 2))\n",
-        "    config = IntervenableConfig(\n",
-        "        representations=[\n",
-        "            RepresentationConfig(\n",
-        "                0,       # layer\n",
-        "                \"block_input\",  # intervention type\n",
-        "            ),\n",
-        "        ] + [\n",
-        "            RepresentationConfig(\n",
-        "                i,       # layer\n",
-        "                stream,  # intervention type\n",
-        "        ) for i in range(start, end)],\n",
-        "        intervention_types=\\\n",
-        "            [NoiseIntervention]+[VanillaIntervention]*(end-start)\n",
-        "    )\n",
-        "    return config\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 28,
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "9152\n"
-          ]
-        }
-      ],
-      "source": [
-        "\n",
-        "\n",
-        "# should finish within 1 min with a standard 12G GPU\n",
-        "token = tokenizer.encode(\"nigger\")[1]\n",
-        "print(token)\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 29,
-      "metadata": {},
-      "outputs": [
-        {
-          "ename": "NameError",
-          "evalue": "name 'counterfactual_outputs' is not defined",
-          "output_type": "error",
-          "traceback": [
-            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-            "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-            "Cell \u001b[0;32mIn[29], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m probabilities \u001b[38;5;241m=\u001b[39m nn\u001b[38;5;241m.\u001b[39mfunctional\u001b[38;5;241m.\u001b[39msoftmax(\u001b[43mcounterfactual_outputs\u001b[49m[\u001b[38;5;241m0\u001b[39m], dim\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28mprint\u001b[39m(probabilities)\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28mprint\u001b[39m(counterfactual_outputs)\n",
-            "\u001b[0;31mNameError\u001b[0m: name 'counterfactual_outputs' is not defined"
-          ]
-        }
-      ],
-      "source": [
-        "\n",
-        "\n",
-        "probabilities = nn.functional.softmax(counterfactual_outputs[0], dim=-1)\n",
-        "print(probabilities)\n",
-        "print(counterfactual_outputs)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 32,
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stderr",
-          "output_type": "stream",
-          "text": [
-            " 83%|████████▎ | 10/12 [00:03<00:00,  3.33it/s]\n"
-          ]
-        },
-        {
-          "ename": "KeyboardInterrupt",
-          "evalue": "",
-          "output_type": "error",
-          "traceback": [
-            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
-            "Cell \u001b[0;32mIn[32], line 12\u001b[0m\n\u001b[1;32m     10\u001b[0m n_restores \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlen\u001b[39m(config\u001b[38;5;241m.\u001b[39mrepresentations) \u001b[38;5;241m-\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m     11\u001b[0m intervenable \u001b[38;5;241m=\u001b[39m IntervenableModel(config, gpt)\n\u001b[0;32m---> 12\u001b[0m _, counterfactual_outputs \u001b[38;5;241m=\u001b[39m \u001b[43mintervenable\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     13\u001b[0m \u001b[43m    \u001b[49m\u001b[43mbase\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     14\u001b[0m \u001b[43m    \u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43mbase\u001b[49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mn_restores\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     15\u001b[0m \u001b[43m    \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m     16\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msources->base\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     17\u001b[0m \u001b[43m            \u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43m[\u001b[49m\u001b[43m[\u001b[49m\u001b[43mpos_i\u001b[49m\u001b[43m]\u001b[49m\u001b[43m]\u001b[49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mn_restores\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     18\u001b[0m \u001b[43m            \u001b[49m\u001b[43m[\u001b[49m\u001b[43m[\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m2\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m]\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43m[\u001b[49m\u001b[43m[\u001b[49m\u001b[43mpos_i\u001b[49m\u001b[43m]\u001b[49m\u001b[43m]\u001b[49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mn_restores\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     19\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     20\u001b[0m \u001b[43m    \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     21\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     22\u001b[0m \u001b[38;5;66;03m#distrib = embed_to_distrib(\u001b[39;00m\n\u001b[1;32m     23\u001b[0m     \u001b[38;5;66;03m#gpt, counterfactual_outputs.last_hidden_state, logits=False\u001b[39;00m\n\u001b[1;32m     24\u001b[0m \u001b[38;5;66;03m#)\u001b[39;00m\n\u001b[1;32m     25\u001b[0m \u001b[38;5;66;03m#prob = distrib[0][-1][token].detach().cpu().item()\u001b[39;00m\n\u001b[1;32m     26\u001b[0m logits \u001b[38;5;241m=\u001b[39m counterfactual_outputs[\u001b[38;5;241m0\u001b[39m]\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/pyvene/models/intervenable_base.py:1424\u001b[0m, in \u001b[0;36mIntervenableModel.forward\u001b[0;34m(self, base, sources, unit_locations, source_representations, subspaces, labels, output_original_output, return_dict)\u001b[0m\n\u001b[1;32m   1420\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1421\u001b[0m     \u001b[38;5;66;03m# intervene\u001b[39;00m\n\u001b[1;32m   1422\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmode \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparallel\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m   1423\u001b[0m         set_handlers_to_remove \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m-> 1424\u001b[0m             \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_wait_for_forward_with_parallel_intervention\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1425\u001b[0m \u001b[43m                \u001b[49m\u001b[43msources\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1426\u001b[0m \u001b[43m                \u001b[49m\u001b[43munit_locations\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1427\u001b[0m \u001b[43m                \u001b[49m\u001b[43mactivations_sources\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1428\u001b[0m \u001b[43m                \u001b[49m\u001b[43msubspaces\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1429\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1430\u001b[0m         )\n\u001b[1;32m   1431\u001b[0m     \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmode \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mserial\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m   1432\u001b[0m         set_handlers_to_remove \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m   1433\u001b[0m             \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_wait_for_forward_with_serial_intervention(\n\u001b[1;32m   1434\u001b[0m                 sources,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1438\u001b[0m             )\n\u001b[1;32m   1439\u001b[0m         )\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/pyvene/models/intervenable_base.py:1072\u001b[0m, in \u001b[0;36mIntervenableModel._wait_for_forward_with_parallel_intervention\u001b[0;34m(self, sources, unit_locations, activations_sources, subspaces)\u001b[0m\n\u001b[1;32m   1063\u001b[0m             get_handlers \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_intervention_getter(\n\u001b[1;32m   1064\u001b[0m                 [key],\n\u001b[1;32m   1065\u001b[0m                 [\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1069\u001b[0m                 ],\n\u001b[1;32m   1070\u001b[0m             )\n\u001b[1;32m   1071\u001b[0m             group_get_handlers\u001b[38;5;241m.\u001b[39mextend(get_handlers)\n\u001b[0;32m-> 1072\u001b[0m         _ \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43msources\u001b[49m\u001b[43m[\u001b[49m\u001b[43mgroup_id\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1073\u001b[0m         group_get_handlers\u001b[38;5;241m.\u001b[39mremove()\n\u001b[1;32m   1074\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1075\u001b[0m     \u001b[38;5;66;03m# simply patch in the ones passed in\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/transformers/models/bert/modeling_bert.py:1564\u001b[0m, in \u001b[0;36mBertForSequenceClassification.forward\u001b[0;34m(self, input_ids, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, labels, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m   1556\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124mr\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m   1557\u001b[0m \u001b[38;5;124;03mlabels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):\u001b[39;00m\n\u001b[1;32m   1558\u001b[0m \u001b[38;5;124;03m    Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,\u001b[39;00m\n\u001b[1;32m   1559\u001b[0m \u001b[38;5;124;03m    config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If\u001b[39;00m\n\u001b[1;32m   1560\u001b[0m \u001b[38;5;124;03m    `config.num_labels > 1` a classification loss is computed (Cross-Entropy).\u001b[39;00m\n\u001b[1;32m   1561\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m   1562\u001b[0m return_dict \u001b[38;5;241m=\u001b[39m return_dict \u001b[38;5;28;01mif\u001b[39;00m return_dict \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39muse_return_dict\n\u001b[0;32m-> 1564\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbert\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1565\u001b[0m \u001b[43m    \u001b[49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1566\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1567\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtoken_type_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken_type_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1568\u001b[0m \u001b[43m    \u001b[49m\u001b[43mposition_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mposition_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1569\u001b[0m \u001b[43m    \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1570\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs_embeds\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minputs_embeds\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1571\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1572\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1573\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1574\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1576\u001b[0m pooled_output \u001b[38;5;241m=\u001b[39m outputs[\u001b[38;5;241m1\u001b[39m]\n\u001b[1;32m   1578\u001b[0m pooled_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdropout(pooled_output)\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/transformers/models/bert/modeling_bert.py:1013\u001b[0m, in \u001b[0;36mBertModel.forward\u001b[0;34m(self, input_ids, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, encoder_hidden_states, encoder_attention_mask, past_key_values, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m   1004\u001b[0m head_mask \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_head_mask(head_mask, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mnum_hidden_layers)\n\u001b[1;32m   1006\u001b[0m embedding_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39membeddings(\n\u001b[1;32m   1007\u001b[0m     input_ids\u001b[38;5;241m=\u001b[39minput_ids,\n\u001b[1;32m   1008\u001b[0m     position_ids\u001b[38;5;241m=\u001b[39mposition_ids,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1011\u001b[0m     past_key_values_length\u001b[38;5;241m=\u001b[39mpast_key_values_length,\n\u001b[1;32m   1012\u001b[0m )\n\u001b[0;32m-> 1013\u001b[0m encoder_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoder\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1014\u001b[0m \u001b[43m    \u001b[49m\u001b[43membedding_output\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1015\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextended_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1016\u001b[0m \u001b[43m    \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1017\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1018\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoder_attention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoder_extended_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1019\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1020\u001b[0m \u001b[43m    \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_cache\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1021\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1022\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1023\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1024\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1025\u001b[0m sequence_output \u001b[38;5;241m=\u001b[39m encoder_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m   1026\u001b[0m pooled_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpooler(sequence_output) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpooler \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/transformers/models/bert/modeling_bert.py:607\u001b[0m, in \u001b[0;36mBertEncoder.forward\u001b[0;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_values, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m    596\u001b[0m     layer_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_gradient_checkpointing_func(\n\u001b[1;32m    597\u001b[0m         layer_module\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__call__\u001b[39m,\n\u001b[1;32m    598\u001b[0m         hidden_states,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    604\u001b[0m         output_attentions,\n\u001b[1;32m    605\u001b[0m     )\n\u001b[1;32m    606\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 607\u001b[0m     layer_outputs \u001b[38;5;241m=\u001b[39m \u001b[43mlayer_module\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    608\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    609\u001b[0m \u001b[43m        \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    610\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlayer_head_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    611\u001b[0m \u001b[43m        \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    612\u001b[0m \u001b[43m        \u001b[49m\u001b[43mencoder_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    613\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    614\u001b[0m \u001b[43m        \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    615\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    617\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m layer_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m    618\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m use_cache:\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/transformers/models/bert/modeling_bert.py:497\u001b[0m, in \u001b[0;36mBertLayer.forward\u001b[0;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions)\u001b[0m\n\u001b[1;32m    485\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\n\u001b[1;32m    486\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    487\u001b[0m     hidden_states: torch\u001b[38;5;241m.\u001b[39mTensor,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    494\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[torch\u001b[38;5;241m.\u001b[39mTensor]:\n\u001b[1;32m    495\u001b[0m     \u001b[38;5;66;03m# decoder uni-directional self-attention cached key/values tuple is at positions 1,2\u001b[39;00m\n\u001b[1;32m    496\u001b[0m     self_attn_past_key_value \u001b[38;5;241m=\u001b[39m past_key_value[:\u001b[38;5;241m2\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m past_key_value \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m--> 497\u001b[0m     self_attention_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mattention\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    498\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    499\u001b[0m \u001b[43m        \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    500\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    501\u001b[0m \u001b[43m        \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    502\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mself_attn_past_key_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    503\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    504\u001b[0m     attention_output \u001b[38;5;241m=\u001b[39m self_attention_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m    506\u001b[0m     \u001b[38;5;66;03m# if decoder, the last output is tuple of self-attn cache\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/transformers/models/bert/modeling_bert.py:427\u001b[0m, in \u001b[0;36mBertAttention.forward\u001b[0;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions)\u001b[0m\n\u001b[1;32m    417\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\n\u001b[1;32m    418\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    419\u001b[0m     hidden_states: torch\u001b[38;5;241m.\u001b[39mTensor,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    425\u001b[0m     output_attentions: Optional[\u001b[38;5;28mbool\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m    426\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[torch\u001b[38;5;241m.\u001b[39mTensor]:\n\u001b[0;32m--> 427\u001b[0m     self_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mself\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    428\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    429\u001b[0m \u001b[43m        \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    430\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    431\u001b[0m \u001b[43m        \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    432\u001b[0m \u001b[43m        \u001b[49m\u001b[43mencoder_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    433\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    434\u001b[0m \u001b[43m        \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    435\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    436\u001b[0m     attention_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput(self_outputs[\u001b[38;5;241m0\u001b[39m], hidden_states)\n\u001b[1;32m    437\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (attention_output,) \u001b[38;5;241m+\u001b[39m self_outputs[\u001b[38;5;241m1\u001b[39m:]  \u001b[38;5;66;03m# add attentions if we output them\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/transformers/models/bert/modeling_bert.py:309\u001b[0m, in \u001b[0;36mBertSelfAttention.forward\u001b[0;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions)\u001b[0m\n\u001b[1;32m    307\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    308\u001b[0m     key_layer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtranspose_for_scores(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkey(hidden_states))\n\u001b[0;32m--> 309\u001b[0m     value_layer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtranspose_for_scores(\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mvalue\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m    311\u001b[0m query_layer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtranspose_for_scores(mixed_query_layer)\n\u001b[1;32m    313\u001b[0m use_cache \u001b[38;5;241m=\u001b[39m past_key_value \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-            "File \u001b[0;32m~/.conda/envs/csproj772/lib/python3.10/site-packages/torch/nn/modules/linear.py:116\u001b[0m, in \u001b[0;36mLinear.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    115\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[0;32m--> 116\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlinear\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbias\u001b[49m\u001b[43m)\u001b[49m\n",
-            "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
-          ]
-        }
-      ],
-      "source": [
-        "\n",
-        "\n",
-        "for stream in [\"block_output\", \"mlp_activation\", \"attention_output\"]:\n",
-        "    data = []\n",
-        "    for layer_i in tqdm(range(gpt.config.num_hidden_layers)):\n",
-        "        for pos_i in range(12):\n",
-        "            config = restore_corrupted_with_interval_config(\n",
-        "                layer_i, stream, \n",
-        "                window=1 if stream == \"block_output\" else 5\n",
-        "            )\n",
-        "            \n",
-        "            n_restores = len(config.representations) - 1\n",
-        "            intervenable = IntervenableModel(config, gpt)\n",
-        "            _, counterfactual_outputs = intervenable(\n",
-        "                base,\n",
-        "                [None] + [base]*n_restores,\n",
-        "                {\n",
-        "                    \"sources->base\": (\n",
-        "                        [None] + [[[pos_i]]]*n_restores,\n",
-        "                        [[[0,1,2,3]]] + [[[pos_i]]]*n_restores,\n",
-        "                    )\n",
-        "                },\n",
-        "            )\n",
-        "            #distrib = embed_to_distrib(\n",
-        "                #gpt, counterfactual_outputs.last_hidden_state, logits=False\n",
-        "            #)\n",
-        "            #prob = distrib[0][-1][token].detach().cpu().item()\n",
-        "            logits = counterfactual_outputs[0]\n",
-        "            probabilities = nn.functional.softmax(logits, dim=-1)\n",
-        "            prob_offense = probabilities[0][0].item()\n",
-        "            data.append({\"layer\": layer_i, \"pos\": pos_i, \"prob\": prob_offense})\n",
-        "    df = pd.DataFrame(data)\n",
-        "    df.to_csv(f\"./tutorial_data/pyvene_rome_{stream}.csv\")\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [
-        {
-          "data": {
-            "text/plain": [
-              "(1, 3, 9, 10)"
-            ]
-          },
-          "execution_count": 69,
-          "metadata": {},
-          "output_type": "execute_result"
-        }
-      ],
-      "source": [
-        "1,3,9,10"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 61,
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stderr",
-          "output_type": "stream",
-          "text": [
-            "/home/shambhavi/.conda/envs/csproj772/lib/python3.10/site-packages/plotnine/ggplot.py:606: PlotnineWarning: Saving 6 x 9 in image.\n",
-            "/home/shambhavi/.conda/envs/csproj772/lib/python3.10/site-packages/plotnine/ggplot.py:607: PlotnineWarning: Filename: ./tutorial_data/pyvene_rome_block_output.pdf\n",
-            "/tmp/ipykernel_36806/1793179634.py:26: FutureWarning: Using print(plot) to draw and show the plot figure is deprecated and will be removed in a future version. Use plot.show().\n"
-          ]
-        },
-        {
-          "data": {
-            "image/png": "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"
-          },
-          "metadata": {
-            "image/png": {
-              "height": 900,
-              "width": 600
-            }
-          },
-          "output_type": "display_data"
-        },
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\n"
-          ]
-        },
-        {
-          "name": "stderr",
-          "output_type": "stream",
-          "text": [
-            "/home/shambhavi/.conda/envs/csproj772/lib/python3.10/site-packages/plotnine/ggplot.py:606: PlotnineWarning: Saving 6 x 9 in image.\n",
-            "/home/shambhavi/.conda/envs/csproj772/lib/python3.10/site-packages/plotnine/ggplot.py:607: PlotnineWarning: Filename: ./tutorial_data/pyvene_rome_mlp_activation.pdf\n",
-            "/tmp/ipykernel_36806/1793179634.py:26: FutureWarning: Using print(plot) to draw and show the plot figure is deprecated and will be removed in a future version. Use plot.show().\n"
-          ]
-        },
-        {
-          "data": {
-            "image/png": "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"
-          },
-          "metadata": {
-            "image/png": {
-              "height": 900,
-              "width": 600
-            }
-          },
-          "output_type": "display_data"
-        },
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\n"
-          ]
-        },
-        {
-          "name": "stderr",
-          "output_type": "stream",
-          "text": [
-            "/home/shambhavi/.conda/envs/csproj772/lib/python3.10/site-packages/plotnine/ggplot.py:606: PlotnineWarning: Saving 6 x 9 in image.\n",
-            "/home/shambhavi/.conda/envs/csproj772/lib/python3.10/site-packages/plotnine/ggplot.py:607: PlotnineWarning: Filename: ./tutorial_data/pyvene_rome_attention_output.pdf\n",
-            "/tmp/ipykernel_36806/1793179634.py:26: FutureWarning: Using print(plot) to draw and show the plot figure is deprecated and will be removed in a future version. Use plot.show().\n"
-          ]
-        },
-        {
-          "data": {
-            "image/png": "iVBORw0KGgoAAAANSUhEUgAABLAAAAcICAYAAAAsUDhKAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8fJSN1AAAACXBIWXMAAB7CAAAewgFu0HU+AADnHklEQVR4nOzdfZyVdZ0//vd1zgw3M9yNgJgpmmGCgprmXZkJmPbdtdIsV0jtbrPtRqvtu9WmlduatmX21dLd7jbNu92f5U3WlqKA5h2ZpoigeYM3KAYjIDADOJw5vz+IWRDmMMxcw/nMmeezx8nDua7r83lfhzPDXK/5fD5XVi6XywEAAAAAiSpUuwAAAAAAqESABQAAAEDSBFgAAAAAJE2ABQAAAEDSBFgAAAAAJE2ABQAAAEDSBFgAAAAAJE2ABQAAAEDSBFgAAAAAJE2ABQAAAEDSBFgAAAAAJK2u2gXkobm5udol9ElNTU1RLBajVCrF8uXLq10OXVAsFqOpqSmWL18epVKp2uWwDb7G+hZfX32Lr6++xddX3+Lrq2/x9dX3bOtrbNSoUVWoCtJnBBYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASaurdgF5KBaL1S6hz/Me9g0b/578ffU9/s7S5+ur7/J3lj5fX32Xv7P0+frq2/y9Qddl5XK5XO0i+pXWV6pdAX2dL9nK2tZVu4KklVtWVLuEtGXVLiBx7e3VriBtBRchdF82fOdqlwC1rXFEtSsAeqgmRmAtX7682iV0WdNAszYBAAB2pJSuGYcNGxbFYjFKpVKsXLlyi+1NTU1VqArSVxMBVqlUqnYJ20GABQAAsCOles2Yal2QImkKAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQtLruHnjCCSfkWMb/GjFiRFx++eW90jYAAAAAfU+3A6xyuZxnHQAAAACwVd0OsCIihgwZEv/8z/+cSyHlcjnOOeecrW676qqr4pprrun02GnTpsX06dNzqaPXrVtd7QoAAAD6laampmqX0KFQKHT8N6W6IHU9CrDq6+tj4sSJedXSqZaWlliyZEmn21tbW6NYLPZ6HQAAAPQ9KV4vZlmWZF2Qqh4FWDtKY2Nj7Lzzzp1ub2hoiFKptAMr6j7fngAAAHaslK4XC4VCZFkW5XI52tvbt9gu1IKty8rdXMyqpaUlsiyLhoaG3IrpbpvNzc251dDbRjXUV7sE+jrrz1XWtq7aFSSt3LKi2iWkLat2AYnbyg/ZbKLggoPuy4Z3/staoOea16yvdgkdmpqaolgsRqlUiuXLl2+xfdSoUVWoCtLX7RFYjY2NedbRa20CAAAA0LcVql0AAAAAAFSyw9bAWr16dSxevDjq6uri9a9/fQwYMGBHdQ0AAABAH9ajAKtUKsVzzz0XERFjx47d6mJzK1eujMsuuyzmzJkTG5fbGjBgQBx33HHxoQ99KOrq+sQ68gAAAABUSY+mEM6dOzc+//nPxwUXXLDV8OrVV1+Ns88+O+67775ob2+Pcrkc5XI51q1bFzfffHN873vf60n3AAAAAPQDPRr+NG/evCiXyzF58uStbr/55pvjueeeiyzLYv/99493vvOdMWjQoJg9e3bcfffdcffdd8exxx4bBxxwQE/KAAAAAKCG9SjAeuyxxyLLsnjLW96y1e233nprZFkW++23X/zrv/5rx+uHHnpoXHDBBXHffffF7NmzBVgAAAAAdKpHUwibm5sjy7J4wxvesMW2v/zlL/HSSy9FRMT73ve+LbafdNJJERHxxBNP9KQEAAAAAGpcjwKsFStWRENDw1YXYn/88ccjIqJYLMb++++/xfa99torsiyL5ubmnpQAAAAAQI3r8V0I169fv9VtTz75ZERE7L777lFfX79lx3V10djYGK2trT0pAQAAAIAa16MRWCNGjIhSqRRLlizZYtvG9bH23nvvTo9fu3ZtDBo0qCclAAAAAFDjehRgjRs3LiI2LNa+qb/85S/x5z//OSIiJk2atNVjX3rppVi/fn2MGjWqJyUAAAAAUON6NIXw6KOPjnvvvTeuv/76aGxsjEMOOSSWLVsWl19+eZTL5WhoaIhDDz10q8fOmzcvIiL23HPPnpQAAAAAQI3rUYB1+OGHx1ve8pb44x//GFdccUVcccUVHduyLIuTTz650ymCd9xxR2RZFvvtt19PSgAAAACgxvVoCmFExJe+9KU47rjjolgsRrlcjnK5HPX19XHKKafEiSeeuNVjFi5cGHPnzo2IiEMOOaSnJQAAAABQw7JyuVzOo6HW1tZ44YUXIiJi7NixMXDgwE73feWVV2LZsmVRLBZj7NixPe67ubm5x23sKKMatrwjI2yXfL5ka1fbumpXkLRyy4pql5C2rNoFJK69vdoVpK1QrHYF9GHZ8J2rXQLUtOY166tdQoempqYoFotRKpVi+fLlW2y3TjRsXY+mEG6qoaGh4h0HNzV8+PAYPnx4Xl0DAAAAUMN6PIWwu1avXh3Tpk2LD37wg9UqAQAAAIA+ILcRWNurvb09WltbI8vM1wAAAACgc1UbgQUAAAAAXSHAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpdT05eN68ed0+trW1tSddAwAAANBP9CjAOvvssyPLsrxqAQAAAIAt9CjAiogol8t51AEAAAAAW9WjAOvHP/5xXnUAAAAAwFb1KMDaeeed86oDAAAAALbKXQgBAAAASFqP18BatWpVNDc3R5Zlseeee25z/3K5HM8++2yUy+UYPXp0DBkypKclAAAAAFDDejwC64ILLojPf/7zccstt3Rp/yzL4pZbbonPf/7zceGFF/a0ewAAAABqXI8CrPnz58ejjz4aI0eOjI997GNdPu6jH/1o7LTTTvHQQw/FE0880ZMSAAAAAKhxPQqw7rzzzsiyLN7znvdEXV3XZyPW19fHe9/73iiXyzF79uyelAAAAABAjetRgPXYY49FRMRhhx223cduPGbBggU9KQEAAACAGtejAGvJkiVRLBZjl1122e5jd9lllygWi/HSSy/1pAQAAAAAalyPAqy1a9fGoEGDun384MGDY+3atT0pAQAAAIAa16MAq7GxMVpbW6O9vX27j21vb4+WlpZobGzsSQkAAAAA1LgeBVijR4+OcrkcTz755HYf++STT0a5XI7Ro0f3pAQAAAAAalyPAqxJkyZFuVyOGTNmbPext956a2RZFpMmTepJCQAAAADUuB4FWFOmTIksy+L222+PBx54oMvHPfDAA3H77bd3tAEAAAAAnelRgLXHHnvE5MmTo1QqxQUXXBA33nhjtLW1dbp/W1tb3HDDDXHBBRdEuVyOd7zjHbHHHnv0pAQAAAAAalxWLpfLPWlg3bp18ZWvfCWefPLJyLIsGhsb48ADD4y99torhgwZEhERq1evjqeffjoeeuihaGlpiXK5HG984xvjggsuiIEDB/b4JJqbm3vcxo4yqqG+2iXQ1/XsS7b2ta2rdgVJK7esqHYJacuqXUDiunHTln6lUKx2BfRh2fCdq10C1LTmNeurXUKHpqamKBaLUSqVYvny5VtsHzVqVBWqgvT1OMCK2BBiXXbZZTF79uwNjWZbvwLY2NXRRx8dn/zkJ2PQoEE97ToiBFj0MwKsygRYFQmwtkGAVZkAqzIBFj0gwILeJcCCvi+XAGujhQsXxm9/+9t45JFH4sUXX9xs26677hqTJk2Kd73rXbHXXnvl1WVECLDoZwRYlQmwKhJgbYMAqzIBVmUCLHpAgAW9S4AFfV+uAdamSqVSrFq1KiIihg4dGsVi7/1QJ8CiXxFgVSbAqkiAtQ0CrMoEWJUJsOgBARb0LgEW9H11vdVwsViMESNG9FbzAAAAAPQT3b4L4cKFC+P555/Ps5ZeaRMAAACAvq3bI7A+97nPRVNTU1x++eW5FdMbbQIAAADQt3V7BBYAAAAA7Ag9WgNr3bp1MXPmzLxqAQAAAIAt9CjAWrNmTVxyySV51QIAAAAAW+h2gDV69Og86+jgzoUAAAAAbKrbAdZPfvKTPOsAAAAAgK2yiDsAAAAASRNgAQAAAJA0ARYAAAAASevRXQhTUSwWq10CAAAAiUr1mjHVuiBFWblcLle7iP7k/9aNqHYJyXu13Ueykld9yVY0os7A0kp2H1gTv7foNXsMrK92CUkrZNWuIG2vrC9Vu4SkDXWRVpF/3ysb5vNTkW/P2zZ16QvVLgHooZq4klm+fHm1SwAAACBRKV0zDhs2LIrFYpRKpVi5cuUW25uamqpQFaSvJgKsUslvPAEAANi6VK8ZU60LUmSuDQAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkLRcAqx77703Pv7xj8fXvva1be77y1/+Mj7+8Y/HD37wgzy6BgAAAKDG5RJgHXDAAbFixYqYO3duLFy4sOK+t9xySyxdujQOOOCAPLoGAAAAoMblEmA1NDTE4YcfHhERs2fP7nS/BQsWxF/+8pfN9gcAAACASuryamjKlClx5513xh133BEf/vCHI8uyLfaZNWtWREQceeSRUV9f3+W2r7rqqrjmmms63T5t2rSYPn369hcNAABAzWtqaqp2CR0KhULHf1OqC1KXW4B14IEHxsiRI2PZsmXxpz/9KQ466KDNtre1tcXdd98dWZbFlClTtqvtlpaWWLJkSafbW1tbo1gsdqtuAAAAaluK14tZliVZF6QqtwAry7J4xzveEddff33Mnj17iwDrj3/8Y6xevTp23XXXGD9+/Ha13djYGDvvvHOn2xsaGqJUKnWrbgAAAGpbSteLhUIhsiyLcrkc7e3tW2wXasHW5RZgRURMnTo1rr/++rjvvvti7dq1MWjQoI5ts2bNiizLYvLkydvd7qmnnhqnnnpqp9ubm5tj+fLl3aoZAACA2pbS9WJTU1MUi8Vob2/fal2jRo2qQlWQvlwWcd9ot912i7333jteffXVuOeeezpeX716dTzwwAMREds9fRAAAACA/i3XACtiQ0BVLpc7FmyPiLjrrrti/fr1MWnSJGkyAAAAANsl9wDrqKOOivr6+njkkUeiubk5Iv53+uDUqVPz7g4AAACAGpd7gDVkyJB4y1veEhERd9xxR7z00kvx2GOPxeDBg+Otb31r3t0BAAAAUONyXcR9o6lTp8a9994bM2fOjLa2toiIeOtb3xoDBgzoje4AAAAAqGG5j8CKiDjooINi+PDh8cILL8SvfvWryLLM4u0AAAAAdEuvBFjFYjHe8Y53RLlcjtbW1th5551jv/32642uAAAAAKhxvRJgRcRmI66MvgIAAACgu3plDayIiDe84Q3xhS98Idra2uLggw/urW4AAAAAqHG9FmBFRBx11FG92TwAAAAA/UCvTSEEAAAAgDwIsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABIWl21C8hDsVisdgkAAAAkKtVrxlTrghTVRIDV1NRU7RK67PChA6tdQvJ2qq+Jj2WvGZBl1S4habvsNLjaJSRt59cNqXYJSRu0x6hqlwA1q1xqr3YJSWtvW1/tEtLm81NRe5v3Z1saE7xmLBaLfepaFqqtJpKC5cuXV7sEAAAAEpXSNeOwYcOiWCxGqVSKlStXbrFdqAVbVxMBVqlUqnYJAAAAJCrVa8ZU64IUWcQdAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKQJsAAAAABImgALAAAAgKTV5dXQT3/604iIeM973hOjR4/Oq1kAAAAA+rncRmDdfPPN8T//8z8xcuTIvJoEAAAAgPxGYI0YMSJeffXVKBTMSgQAAAAgP7mlTePHj4/W1tZYunRpXk0CAAAAQH4B1gknnBCFQiF+9rOf5dUkAAAAAERWLpfLeTV21113xfe///3Ya6+94r3vfW+MHz8+hg8fHlmW9ajdq666Kq655ppOt0+bNi2mT5/eoz52lBtG7VrtEpK3U31uM1tr0oAefj3Vul12GlztEpK28+uGVLuEpA3aY1S1S4CaVS61V7uEpLW3ra92CWnz+amovc37sy2DfnFntUvoUCgUIsuyKJfL0d6+5d9dsVisQlWQvtySghNOOKHj+YIFC2LBggVdOu7GG2/c5j4tLS2xZMmSTre3trb6IgcAAGCrUrxezLIsybogVbkFWN0ZyNXVkVmNjY2x8847d7q9oaEhSqXSdvcPAABA7UvpetEILOie3KYQzps3r1vHTZw4scd9Nzc397iNHWX23vtVu4TkmUJYmSmElZlCWJkphJWZQgi9xxTCykwh3Aafn4pMIdy2NT++qdoldGhqaopisRilUimWL1++xfZRo/w8AluTW1KQRxAFAAAAAK+V210IAQAAAKA39NpcrRUrVsTSpUtj3bp1RmcBAAAA0G25B1j33HNP/Pd//3c8++yzHa9teqfB1atXx3e+852IiPjiF78YjY2NeZcAAAAAQA3JdQrhtddeG9/+9rfjmWeeiXK5vNU7Ew4ZMiQaGxvj4YcfjrvvvjvP7gEAAACoQbkFWPPmzYv/+q//ikKhEKeffnr89Kc/jREjRmx138mTJ0e5XI4HH3wwr+4BAAAAqFG5TSG8+eabI8uyOOWUU+Kkk06quO+ECRMiImLhwoV5dQ8AAABAjcptBNbjjz8eERF/8zd/s819hwwZEoMHD45ly5bl1T0AAAAANSq3AGvlypUxePDgGDJkSNc6LhS2ukYWAAAAAGwqtwCrsbEx1qxZE+vXr9/mvqtWrYrW1tYYNmxYXt0DAAAAUKNyC7D23HPPiPjfqYSV3HHHHVEul2PvvffOq3sAAAAAalRuAdbb3/72KJfLcfXVV1cchfXYY4/FlVdeGVmWxeTJk/PqHgAAAIAaldtdCI855pi49dZbY/78+fGVr3wl/vZv/zZKpVJERDzxxBOxZMmSuP/+++P3v/99rF+/Pvbff/84/PDD8+oeAAAAgBqVW4BVKBTiq1/9anzzm9+Mxx9/PP785z93bPunf/qnjuflcjkmTJgQX/rSl/LqGgAAAIAalluAFRExfPjwuOCCC2L27NkxY8aMePLJJ6OtrS0iNgRce++9dxxzzDExderUKBaLeXYNAAAAQI3KNcCKiCgWizF16tSYOnVqtLe3x+rVq6NUKsWwYcOEVgAAAABst9wDrE0VCoUYNmxYb3YBAAAAQI3L7S6E29Le3h6LFi2KhQsXRnt7+47qFgAAAIA+LrcRWM8//3zceeedMWbMmDjmmGM22zZ37tz4f//v/8WyZcsiImLkyJHxj//4j7Hffvvl1T0AAAAANSq3EVgzZ86M6667Ll555ZXNXl+xYkWcf/758fLLL0e5XI5yuRzNzc3xr//6r9Hc3JxX9wAAAADUqNwCrEceeSQiIo444ojNXr/llltizZo1sdtuu8VFF10U3//+92OfffaJtWvXxs0335xX9wAAAADUqNwCrJdffjkiIsaMGbPZ6/fff39kWRann356vPGNb4yxY8fGP/zDP0S5XI4HH3wwr+4BAAAAqFG5BVgrV66MxsbGKBaLHa+tW7cunnrqqairq4uDDjqo4/W99tor6urqYsmSJXl1DwAAAECNyi3AqqurizVr1mz22mOPPRbt7e2x9957R319/WbbBg0aFKVSKa/uAQAAAKhRuQVYY8aMifb29pg/f37Ha/fee29kWbbF3QZLpVK0trbGiBEj8uoeAAAAgBqVW4B18MEHR7lcjksuuSTuuuuuuPnmm2PGjBkREXH44Ydvtu/ChQujvb09Ro0alVf3AAAAANSourwaOvHEE2P27NmxePHiuPDCCyMiolwux2GHHRbjxo3bbN85c+ZElmWx77775tU9AAAAADUqtwBr2LBh8e1vfzuuvfbaePzxx6OhoSEOPvjgOOmkkzbbb/369TFjxowol8txwAEH5NU9AAAAADUqtwArImL06NFx1llnVe6wri4uv/zyPLsFAAAAoIbltgYWAAAAAPSG3EZgzZw5s1vHTZkyJa8SAAAAAKhBuQVYF198cWRZtt3HCbAAAAAAqCS3AGv06NEVt7e2tkZLS0tERAwaNCiGDh2aV9cAAAAA1LDcAqyf/OQn29xn8eLF8Ytf/CLuuOOOOPXUU+Poo4/Oq3sAAAAAalSudyHclte97nVx5plnxsCBA+OSSy6J173udbHPPvvsyBIAAAAA6GOqchfCv/u7v4v29va47rrrqtE9AAAAAH1IVQKs4cOHR0NDQzz++OPV6B4AAACAPmSHTiHcqKWlJVpaWqK+vr4a3QMAAADQh1RlBNY111wTERvWxAIAAACASnIbgTVz5syK21999dV4+eWX4w9/+EM8++yzkWVZTJkyJa/uAQAAAKhRuQVYF198cWRZts39yuVyREQceeSR8Z73vCev7gEAAACoUbkFWKNHj664vVgsxpAhQ2KPPfaIt7/97fHmN785r64BAAAAqGG5BVg/+clP8moKAAAAADpUZRF3AAAAAOgqARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJA0ARYAAAAASRNgAQAAAJC0umoXkIdisVjtEgAAAEhUqteMqdYFKaqJAKupqanaJXRZfSGrdgnJW9dernYJSVsb7dUuIWnty9ZUu4Sktba2VbuEpA18fmW1S0ja6pb11S4haaWyf78qMey/sqKfESsq1nl/Khmzc0O1S0jemASvGYvFYp+6loVqq4kAa/ny5dUuAQAAgESldM04bNiwKBaLUSqVYuXKLX95JtSCrauJAKtUKlW7BAAAABKV6jVjqnVBiozmBgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAkibAAgAAACBpAiwAAAAAktZrAda6deviU5/6VJxxxhnxwAMP9FY3AAAAANS4Xguw7rnnnnjhhRdiyZIlMWPGjN7qBgAAAIAa12sB1syZMyMiolwux/333x+rVq3qra4AAAAAqGF1vdHo0qVL45FHHon6+vrYZ5994tFHH40777wz/vZv/7Zb7V111VVxzTXXdLp92rRpMX369O6WCwAAQA1ramqqdgkdCoVCx39TqgtS1ysB1qxZs6JcLschhxwSb3/722PevHlx++23dzvAamlpiSVLlnS6vbW1NYrFYnfLBQAAoIaleL2YZVmSdUGqei3AyrIspkyZEgceeGA0NjbG008/Hc8991yMHTt2u9trbGyMnXfeudPtDQ0NUSqVelIyAAAANSql68VCoRBZlkW5XI729vYttgu1YOtyD7Aee+yxePHFF2PYsGFx0EEHRbFYjLe97W0xY8aMuP322+MjH/nIdrd56qmnxqmnntrp9ubm5li+fHlPygYAAKBGpXS92NTUFMViMdrb27da16hRo6pQFaQv90XcZ86cGVmWxVFHHdWRHE+ePDnK5XLccccdW02YAQAAAKAzuQZYbW1t8fvf/z4iNoRWG+27774xZsyYWLFiRTz44IN5dgkAAABAjcs1wJozZ060trbGbrvtFuPGjdts2zve8Y4ol8sxa9asPLsEAAAAoMblGmDdfvvtkWXZZqOvNtr42pw5c6KlpSXPbgEAAACoYbkFWMuXL4+HHnooIiKOPvroLbbvuuuusffee8f69es7phkCAAAAwLbkFmDNnj072tvbY9KkSTFy5Mit7rNxMfeZM2fm1S0AAAAANS63AGvj3Qe3Nn1wo7e//e1RLBbjz3/+cyxatCivrgEAAACoYbkEWE8++WQ899xzMXDgwHjrW9/a6X7Dhg2Lgw46KMrlctx+++15dA0AAABAjavLo5EBAwbEWWedFU1NTTFo0KCK+37oQx+KI444IoYPH55H1wAAAADUuFwCrLFjx8bYsWO7tO/uu+8eu+++ex7dAgAAANAP5LYGFgAAAAD0BgEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEkTYAEAAACQNAEWAAAAAEmrq3YBeSgWi9UuAQAAgESles2Yal2QoqxcLperXUR/suLtk6pdQvIK9TWRq/aarN4/cpWU231LqyQrZNUuIW2Z96eScqm92iUkrdy2vtolJM3np7L2kn+/KinWmThSic/PtjXd/Ui1SwB6qCaSguXLl1e7hC5zaQQAALBjpXTNOGzYsCgWi1EqlWLlypVbbG9qaqpCVZC+mgiwSqVStUvospp4wwEAAPqQVK8ZU60LUmQsLgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJE2ABAAAAkDQBFgAAAABJq8ujkbPPPnu7j8myLM4777w8ugcAAACghuUSYM2bN69L+2VZFhER5XK54zkAAAAAVJJLgHXKKadU3N7a2hpPPPFELFiwIIYMGRL/5//8nygWi3l0DQAAAECNyyXAmjZtWpf2e/TRR+P888+PZ555Js4555w8ugYAAACgxu3QRdz322+/+OQnPxl//OMf49e//vWO7BoAAACAPiqXEVjb44gjjohisRgzZsyI448/vkvHXHXVVXHNNdd0un3atGkxffr0vErsVauqXQAAAEA/09TUVO0SOhQKhY7/plQXpG6HB1jFYjHq6upi8eLFXT6mpaUllixZ0un21tZWa2oBAACwVSleL2ZZlmRdkKodHmA9++yzsXbt2mhoaOjyMY2NjbHzzjt3ur2hoSFKpVIe5QEAAFBjUrpeLBQKkWVZlMvlaG9v32K7UAu2bocGWE899VRcfPHFkWVZvOlNb+rycaeeemqceuqpnW5vbm6O5cuX51Fir9vhiSEAAEA/l9L1YlNTUxSLxWhvb99qXaNGjapCVZC+XPKUs88+u+L2tra2aG5ujmXLlkW5XI5isRgnn3xyHl0DAAAAUONyCbDmzZvX5X1HjhwZn/zkJ2O//fbLo2sAAAAAalwuAdYpp5xScXuxWIwhQ4bEHnvsERMmTOi46wIAAAAAbEsuAda0adPyaAYAAAAAtmAoFAAAAABJE2ABAAAAkLRcphBu1N7eHvfcc0/cdddd8eSTT8Yrr7wSERHDhw+PcePGxVFHHRVHHHFEZFmWZ7cAAAAA1LDcAqyXX345LrjggnjyyScjIqJcLndsW7p0aSxdujTuu+++2HvvvePLX/5yjBw5Mq+uAQAAAKhhuQRY69ati6997WuxaNGiyLIsDjzwwDjggANi1KhRERHR3NwcDz/8cDz00EPxxBNPxNe+9rX43ve+FwMGDMijewAAAABqWC4B1q9//etYtGhRDB8+PP75n/85JkyYsMU+J554YsyfPz8uuOCCeOGFF+LXv/51vO9978ujewAAAABqWC6LuN99992RZVl8+tOf3mp4tdG+++4bn/70p6NcLsddd92VR9cAAAAA1LhcAqwXX3wx6urq4tBDD93mvoceemjU19fHiy++mEfXAAAAANS4XAKs9evXR319fZfuLlgoFKK+vj7Wr1+fR9cAAAAA1LhcAqzRo0fHmjVr4plnntnmvgsXLozW1tYYPXp0Hl0DAAAAUONyCbAOPPDAKJfLcdlll0Vra2un+61ZsyYuu+yyyLIs3vzmN+fRNQAAAAA1Lpe7EL7vfe+LmTNnxp///Of4zGc+E+9973tj0qRJMXLkyIiIePnll+Phhx+OX//619Hc3ByDBg1yB0IAAAAAuiSXAGv06NHx5S9/Of7t3/4tXn755fjZz3621f3K5XIMHjw4vvSlL8WoUaPy6BoAAACAGpfLFMKIiDe/+c1xySWXxDvf+c5obGyMcrm82aOxsTGOO+64+P73v2/6IAAAAABdlpXL5XJvNPzSSy/FK6+8EhERw4cPj1122aU3uomIiObm5l5rO291J06udgnJK9TnMjCwZmX1xWqXkLRye698S6sZWWHbd4vt17pwN93+rFxqr3YJSSu3ucNyJT4/lbWX/PtVSbEut9+71ySfn20r3TSr2iV0aGpqimKxGKVSKZYvX77FdrOVYOtySQpuuummmDJlSgwdOrTjtV122aVXQysAAAAA+odcfpXxn//5n/GRj3wkvvOd78Sf/vSnPJoEAAAAgIjIaQTWmDFj4i9/+Uvcddddcffdd8eoUaPimGOOiWOOOcbwRwAAAAB6JLc1sB555JG49dZb49577422trbIsiyyLIsDDzww3vnOd8Zhhx0WxWLvrN1jDazaYg2syqyBVZk1sCqzBtY2WAOrImsYVWYNrMp8fiqzhlFl1sCqzOdn26yBBX1fbknBpEmTYtKkSdHS0hJ33HFH3HbbbfHUU0/Fgw8+GH/6059i6NChMWXKlDjmmGNi9913z6tbAAAAAGpcr92FMCJi4cKFceutt8add94Zq1evjuyvv9l+05veFMcee2y8/e1vj4EDB/a4HyOwaosRWJUZgVWZEViVGYG1DUZgVWQETWVGYFXm81OZETSVGYFVmc/PthmBBX1frwZYG7W1tcW9994bv/rVr+KJJ57oCLIGDRoURx11VLz73e/u0agsAVZtEWBVJsCqTIBVmQBrGwRYFQkgKhNgVebzU5kAojIBVmU+P9smwIK+b4f8S/Doo4/GnDlz4plnnomIiI2Z2Zo1a+LWW2+Ns846K/7jP/4jSqXSjigHAAAAgD6k14a6LF26NG677ba4/fbbo7m5uSO02nfffeO4446Lww8/PB555JH47W9/Gw888ED87ne/i2HDhsX06dN7qyQAAAAA+qBcA6y2tra477774rbbbouHH344IjaMtho6dGhMnjw5jjvuuNhtt9069j/kkEPikEMOiTvvvDO++93vxqxZswRYAAAAAGwmlwBr4cKFcdttt8Xs2bOjpaWlY7TVxIkT47jjjosjjjgi6uvrOz3+qKOOih/96Ed9ai0rAAAAAHaMXAKsz33uc5FlWZTL5Rg2bFhMnTo1jj322Nh111273MagQYNi9erVeZQDAAAAQA3JbQrhpEmTOta2qqvb/mb/7d/+zSLuAAAAAGwhlwDrhz/8Yeyyyy49amPkyJF5lAIAAABAjSnk0UhPwysAAAAA6EwuARYAAAAA9BYBFgAAAABJE2ABAAAAVdfW1hYTJkyILMviC1/4wlb3ybIssiyLo48+escWl6hHHnkkisViZFkWs2fPrnY5vUqABQAAAFTd9773vXjsscdixIgRcc4551S7nO1y+eWXx7nnnhvnnnvuDu130qRJcfrpp0dExGc+85kolUo7tP8dSYAFAAAAVNWyZcvi/PPPj4iIM888M5qamqpc0fa5/PLL41/+5V/iX/7lX3Z431/5yleiUCjEo48+GpdffvkO739HEWABAAAAVXXhhRfGK6+8EoMGDYrPfvaz1S6nT9l7773jfe97X0REfOMb34i2trYqV9Q7BFgAAABA1axevTr+/d//PSIiPvCBD8TIkSOrXFHf8w//8A8REfHcc8/F//f//X9VrqZ3CLAAAACAqrn66qtjxYoVERHxoQ99qLrF9FFTpkyJ3XbbLSIifvCDH1S5mt4hwAIAAAC6bPbs2R13A9y4aPnjjz8eZ555Zuyzzz7R2NgYTU1Ncfjhh8f3vve9WLduXcX2Nq7bNHLkyO2+u+DatWvjkksuiSOOOCJGjhwZgwcPjnHjxsUnP/nJWLhw4TaPX7RoUVx22WVxyimnxL777htDhw6N+vr6GDVqVBx22GHxz//8z/H88893evzRRx8dWZbFHXfc0fHaxvdm08eHP/zhTtu4884744wzzogJEybEiBEjYtCgQbH77rvHSSedFL/85S+jXC5v8zyyLOuYRnjffffF448/vs1j+pq6ahcAAAAA9F3//d//HR/96EejtbW147XW1taYM2dOzJkzJ370ox/F7373u9hjjz22OHbx4sVx3333RUTE2972tigWi13ud+HChfHe9743Hnnkkc1ef+qpp+Kpp56KK6+8Mn796193GorNnj07pkyZstWA6OWXX46XX345/vCHP8RFF10Ul112WXzsYx/rcm1dsWLFijjttNPi17/+9RbbFi1aFIsWLYrrr78+jjrqqPjlL38Zo0aNqtje0UcfHZdccklERNxwww3x5S9/Odd6q02ABQAAAHTLAw88EN/61reira0tpk+fHlOnTo3BgwfHo48+Gv/5n/8ZixcvjsceeywmT54cf/rTn2L48OGbHX/LLbd0PD/88MO73O/KlSvjb//2b2PBggVx7LHHxrvf/e4YM2ZMLF68OK644op48MEHo6WlJU455ZRYsGDBVu9quHbt2iiXy7HPPvvE5MmTY999941Ro0ZFXV1dvPTSS3HnnXfGjTfeGK+++mp8/OMfjzFjxsTxxx+/WRvnnXdeNDc3xznnnBOPPvpoRGwIj15r7NixW9T/tre9LebPnx8RGxZi/8AHPhATJkyIAQMGxNNPPx3XXnttzJ07N+6888445phj4r777otBgwZ1+p5s+v797ne/q7kAKyt3ZSxa4pqbm6tdQpfVnTi52iUkr1AvV60kq+/6byT6o3J7n/+W1quyQlbtEtKWeX8qKZfaq11C0spt66tdQtJ8fiprL/n3q5JinZVPKvH52bbSTbOqXUKHpqamKBaLUSqVYvny5Vts39YomxTMnj07Jk/+32vbhoaG+M1vfrPFSKcVK1bE3/zN38S9994bERGf+MQn4j/+4z822+eTn/xkx2u33357TJkypWLf2SY/r9XV1cW1114b73//+zfbZ/369fHud787fve730VExHe/+934x3/8xy3aevbZZ2PFihVxwAEHdNrfQw89FMcdd1wsWbIk9t5773j88cc3q2Gjo48+umMaYVdilmnTpsV//dd/RUTEueeeG+ecc84Wo8/a29vji1/8Ynz3u9+NiIizzz47zjvvvIrt7rnnnvHss89GQ0NDrFy5crtGtKXOvwQAAABAt33rW9/a6jS9ESNGxHXXXRdDhgyJiA1rXS1dunSzfTad/jd+/Pjt6vcrX/nKFuFVxIZg63vf+17Hn3/7299u9fg99tijYngVEXHggQfG+eefHxERTzzxRNxzzz3bVePWzJ07tyO8+tjHPhZf//rXtxo0FQqFuPDCC+Ntb3tbRGxYnH1b64lNmDAhIjZM4Xzqqad6XGtKBFgAAABAt4wYMSI+/vGPd7r99a9/fXzwgx+MiIh169bFzTffvNn2Z555puP5Tjvt1OV+C4VCfPazn+10+/jx4zvuyjdv3rwut7s1Rx55ZMfzjet19cQVV1zR8fyLX/ziNvc//fTTIyLilVdeiTlz5lTcd9P3cNP3thaYqwUAAAB0y5FHHllxXaaIiGOOOSZ++MMfRkTEH/7wh/joRz/asW3ZsmURsWEa4rba2dQ+++yzzcBrt912i0WLFm11quamHnroobjqqqvi3nvvjSeeeCJWrlzZ6UinRYsWdbnGztx5550RETFo0KCYP39+xzpYnXnhhRc6ns+fPz+OOuqoTvcdOXJkx/ON722tEGABAAAA3bL33ntv1z4vvvjiZts2BkVDhw7drn67slbYwIEDN+vjtdavXx+f/vSn48c//nGX1q2K2LD4ek9tHBm1du3aOPHEE7fr2G2FUsOGDet4vmbNmu2uLWUCLAAAAKBbGhsbt2ufVatWbbZt4MCBsWbNmu0OhgqFnq+I9NnPfjZ+9KMfRUREfX19vOtd74pDDz00dtttt2hsbIz6+vqIiFiyZEl84hOfiIiIUqnU435XrFjR7WNfffXVittfeeWVjueDBw/udj8pEmABAAAA3dLS0rJd+7x2pNXIkSNj0aJFsWbNmli7du12TSPsieeff77j7oevf/3rY9asWZ2OJnv00Udz7XvIkCGxYsWK2GmnneLll1/Ote1N29ueNcX6Aou4AwAAAN3y5JNPbtc+u+6662bb3vCGN3Q835FrNt12223R3t4eERFf/vKXK06FXLhwYa59b1xcfsWKFbF69epc2970Pdxzzz1zbbvaBFgAAABAt/z+97/vdI2pjW677baO54cddthm2yZNmtTxfMGCBfkWV8FLL73U8XzcuHEV9/3tb3+7zfY2ndK4rfW03vGOd0RERHt7e9xyyy3bbHt7bFwQvrGxMd74xjfm2na1CbAAAACAblmxYkX85Cc/6XT74sWL4+qrr46IDetdHX/88ZttP/zwwzuez5kzp3eK3IpN1+WqNIrs6aefjiuuuGKb7Q0ZMqTj+bamVZ5++ukdz7/xjW/E2rVrt9l+VyxevDief/75iIg45JBDolgs5tJuKgRYAAAAQLd96UtfijvvvHOL11euXBknn3xyx8LtH/nIR2L06NGb7XPsscdGlmURsWMDrEMOOaTj+YUXXrjVtaiee+65ePe7392ldb42nQr54IMPVtz30EMPjQ984AMRETF37tx473vfG0uXLu10/3K5HHfffXf83//7fyu2e++993Y8P+6447ZZc19jEXcAAACgW44//viYMWNGTJkyJU455ZSYOnVqDB48OObPnx8//elP48UXX4yIDQHPv/3bv21x/JgxY+Jtb3tb3HXXXXHXXXdFW1tbx93/etMRRxwRhx12WMyZMyeeffbZGD9+fJxxxhkxYcKEKJVKcd9998WVV14ZLS0t8eEPfzguv/zyiu0dc8wxcckll0RExMc+9rH47Gc/G294wxs6RkG9/vWv32y65E9/+tP485//HA8//HDceuutseeee8ZJJ50Uhx9+eIwePTra2triL3/5S8ydOzduu+22WLRoUbzxjW+MCy+8sNMaNg0RTzzxxB68O2kSYAEAAADdcvDBB8dpp50WH/nIR+Lqq6/umC64qX322Sd+97vfxbBhw7baxumnnx533XVXLFu2LH7zm9/ECSec0MtVb/Bf//VfMWXKlFi4cGE0NzfH+eefv8U+Z555Znz+85/fZoD1N3/zN/GOd7wj7rjjjnjyySfjzDPP3Gz7hz70oc3aGDp0aNx1113xqU99Kq666qpobW2NK6+8Mq688spO+9i4+PvWlMvluP766yNiwzpj++yzT8V6+6KamEJYLBb7zAMAAIAdq9rXgZ1dE9bKNePJJ58cDz74YHz605+OvffeOxoaGmL48OFx6KGHxne/+914+OGHK94Rb/r06dHU1BQRET//+c93UNUb7tL3pz/9Kc4999zYf//9o6GhIRoaGmKvvfaKU089NWbNmhWXXHJJxxTHSorFYtxyyy1x4YUXxtve9rbYaaedoq6u8pihIUOGxM9//vOYN29e/NM//VMceuihMXr06Kirq4uGhobYY4894thjj41zzz035syZE7Nnz+60rVmzZnWsf/WZz3xmu96HviIrb2t5fHK18piDql1C8goDe3+4aF+WFWsid+41vqXRE1354aQ/K5faq10CfVj7q+urXULSym3eH7qvvc33521puvuRapdQU2bPnh2TJ0+OiIivf/3rce655/a4zXPOOSe++c1vxoABA2LRokVbrJVFZSeffHJcd911sfvuu8dTTz21Q6Zh7mg1MYVw+fLl1S6hy/pmng4AANB3pXTNOGzYsCgWi1EqlWLlypVbbN84Eqm/+cIXvhA/+MEP4pVXXolvf/vb8Z3vfKfaJfUZTz75ZMf0wa997Ws1GV5F1EiAVSqVql1ClwmwAAAAdqxUrxlTrasampqa4itf+Up86UtfiksvvTS+8IUvxC677FLtsvqE888/P0qlUuy7777x4Q9/uNrl9BpzkQAAAICq+/znPx/jx4+PNWvWbHVBdbY0b968uOKKKyIi4tJLL93mult9We2eGQAAANBn1NfXx4IFC6pdRp8yceLEfjOSzwgsAAAAAJJmBBYAAADQZUcffbS7f7PDGYEFAAAAQNIEWAAAAAAkTYAFAAAAQNIEWAAAAAAkzSLuAAAAQEXffcf/iWf+8EBElkWWRURkkWVZRBZ/fS3762ub/jn+us+G57HxuI2NZhueb1wOPou/trepjTtkf31Sce34cmy2tvwmf+hYdL68cZ/yhtc2+fOG51v+OcoRr9tvfHzlj3d25a2ilwiwAAAAgIoW3vuHKLW15dZeNe5h+NpsbHs8/+DDudVB9wiwAAAAgMrK7d0+dGvBUU/CpJ7odnBWrkbkxqYEWAAAAEBFhciinFPqlO3A+Kr8msiqWsEZPSfAAgAAACrKYkOI1Vtt5+W146R2ZFhG7xJgAQAAABVlWblPREF9oUa6R4AFAAAAVJRtvMNg1fqvzsLvm/ZPdQmwAAAAgIoK1S4gqhsiCbCqT4AFAAAAVFTMsqjqECz6PQEWAAAAUFGWZUmMwqoa4V3VCbAAAACAigpZuV/Po5NfVZ8ACwAAAKio0J/Tq9gwAo3qEmABAAAAFWXRrwdgRZSreQ9EIgRYAAAAQBf061FI/fncEyHAAgAAACoqZFm0V7uIKpJfVZ8ACwAAAKisvGV8VcuZzmsnDJbbTSGsNgEWAAAAUFGhC4tg9eVA67XxVF8+l1olwAIAAAAqKnRjDl3KIZDAqu8RYAEAAAAVZZFtGIXVwzaqpfyayEpg1fcIsAAAAICKCllEex+OfaoZnpEPARYAAABQUVYu93oE1JP2LbFe+wRYAAAAQEWFLNvh8+4qdWcNq/5HgAUAAABUVKh2Aa8hsOp/BFgAAABARakFWDuaNbSqT4AFAAAAVFQoZBHtQhyqR4AFAAAAVFTo76ukZ8K7ahNgAQAAAJVlJtFRXQIsAAAAoKL+PoPQAKzqE2ABAAAAFRWiv88hpNr6+40EAAAAgG3IIotC1r8fPbV06dL4whe+EHvvvXcMHjw4Ro0aFccee2zceOONPWq3ra0tLrroojj44INj2LBhMWzYsHjLW94S3/ve96Ktra3T4x588MH4+te/HpMnT44xY8ZEfX19jBgxIo444oj41re+FStXruy1vrsjK5fLfT5GbW5urnYJXTbglGOrXULyCgPrq11C0rKi3LmSGviWRhVlxoZXVC61V7sE+rD2V9dXu4Skldu8P3Rfe5vvz9tSumlWtUvo0NTUFMViMUqlUixfvnyL7aNGjapCVdt26bCdI9r792ft06u7nz08+uijMWXKlFiyZElERAwdOjRaW1ujVCpFRMRZZ50VF1988Xa3u3r16jjmmGNizpw5ERExaNCgiIhYu3ZtREQcccQRMWPGjGhsbNzsuKuvvjpOPfXUjj9nWRbDhw+PV155peOaauzYsfHb3/429t1331z77i5XwgAAAEBFhSwiiy0fhRp8bO08e/JrznXr1sV73vOeWLJkSUycODEeeuihWLlyZaxcuTLOO++8yLIsLrnkkvjZz3623W1/4hOfiDlz5sSIESPi+uuvj9bW1mhtbY3rr78+RowYEffee2986lOf2uK4tra2GDx4cHz0ox+NGTNmREtLSyxfvjxWrVoVV1xxRYwaNSqee+65OP7442PNmjW59t1dRmDtYEZgbZsRWJUZgVVZDXxLo4qMwKrMCCx6wgisyozAoieMwNo2I7B67kcjxkT7X0cLVdIXf5rq6hXEP6zqXvbw/e9/P84666xoaGiIBQsWxNixYzfb/pnPfCYuvfTS2HXXXeOZZ56J+vquXRPPnTs3DjzwwCiXy/GLX/wiTjrppM22/+IXv4gPfOADkWVZzJ07NyZOnNix7fHHH4/hw4fHLrvsstW2Z82aFVOmTImIiCuuuCJOP/303PruLlfCAAAAQEVZZFHowuO1/+vKMTv60d0au+uqq66KiIhp06ZtEV5FRHzxi1+MLMvixRdfjFmzuh62Xn311VEul2PcuHHxvve9b4vtJ510UowbNy7K5XJcc801m23bZ599Og2vIiImT54ce+yxR0REPPDAA7n23V0CLAAAAKCirJMphNt6pKg759Hdc1m9enXcf//9ERHxrne9a6v7jB07NiZMmBAREbfffnuX2545c2ZERBx33HFbnUmQZVkce+yx293uRhtHA65fv+Uo4d7ue2vqcmkFAAAAqFmFiGjvhUSqN0KulBYVWbBgQccyJ5Wm0U2cODHmz58f8+fP71K75XI5FixY0KV2N9axPZYtWxbz5s3bavu93XdnBFgAAABARVm53GemcKU08mvx4sUdz3fddddO99u4bdP9K1m1alW0tLR0ud1Vq1bF6tWrY8iQIV1q/xvf+EasW7cuhg4dGu9///t3aN+d6SufPwAAAKBKCoWs21PvevooZP/7qFYN3b3Xz+rVqzueNzQ0dLrfxm2rVq3qlXa3p+3f/OY38f3vfz8iNgRZo0eP3mF9V2IEFgAAAFBRIbIkhjZV76bRCZz8DvDQQw/F9OnTo729PU444YT47Gc/W+2SOgiwAAAAgIqyLGLUB94XI9+/5R3nOvPyL66PZb+4oRer6r6d3n/idp1Ld89j02lzra2tMWzYsK3u19raGhERQ4cO7Va7ndl027baXrBgQRx77LGxcuXKOProo+Paa6/d6gLtvdF3VwiwAAAAgIoKEVHX0BD1o0d1+Zi6hoZk1y3a3nMpNnY+Va6STdeIevHFFzsNsF588cWIiHjd617XpXaHDh0aQ4YMidWrV3ccW6ndjft35oknnoipU6fG0qVL4/DDD4+bb745Bg0atEP67ioBFgAAAFBRlmXR3toabUubu3xMe2trshPvtvtcWjofaVTJ+PHjI8uyKJfL8eijj8b48eO3ut+jjz4aERH77rtvl9rNsiwmTJgQ999/f8exldqdMGFCp/s8/fTTMWXKlFi8eHG8+c1vjt/+9rcVA6c8+94eAiwAAACgoiwiVvzihlixnVPpUg2wtvtcsiziJ/+x3f0MGTIkDj300JgzZ0787ne/i5NOOmmLfRYtWhTz58+PiIipU6d2ue0pU6bE/fffH7fcckun+9x6660V23322Wdj8uTJsWjRopg4cWLceuutMWLEiB3S9/ZKdTQfAAAAkIgs8+iuD37wgxERce2118bzzz+/xfZvf/vbUS6XY9ddd43Jkyd3ud3p06dHlmXxxBNPxA03bBnGXX/99fHEE09ElmUdNWzqhRdeiClTpsRzzz0X++yzT9x2220xalTXplX2tO/u6JUAq1QqxZ///Oe4++67Y+bMmb3RBQAAALCDFMob7kTYnx/ddcYZZ8Ree+0VLS0tcfzxx8fcuXMjImLNmjXxrW99K37wgx9ERMR5550X9fX1mx275557RpZl8eEPf3iLdvfff/+YNm1aRER87GMfi5tuuinK5XKUy+W46aab4u///u8jIuK0006L/fbbb7NjlyxZElOnTo2nn3463vjGN8btt98eY8aM6fI59aTv7sp9CuGNN94Yv/jFL2L16tUdr02ZMqXj+erVq+Of//mfY/369XH++edHU1NT3iUAAAAAOUp1KmBfMHDgwPjVr34VU6ZMiblz58YBBxwQw4YNi5aWliiVShERceaZZ8ZHPvKR7W77hz/8YTz11FMxZ86cOOGEE2Lw4MFRLpdj7dq1ERFxxBFHxGWXXbbFcf/xH/8Rjz/+eERsCLMOPvjgTvt461vfGtdff31ufXdXriOwLrnkkrj88stj1apVUVe39WxsyJAh8aY3vSkWL14cd911V57dAwAAAL2gXC5Xu4Tq6uH577fffvHII4/E5z//+Rg3blysW7cuhg8fHsccc0zccMMNcckll3Sr3SFDhsTvf//7+O53vxsHHXRQFIvFqKuri4MOOiguuuiiuOOOO6KxsXGL49rb2zuer1q1Kv7yl790+li2bFmufXdXVs7pU3jffffFBRdcEA0NDfHpT386jjjiiPjoRz8ar7zyStx4442b7Tt37tz46le/Goccckicc845Pe67ubnrdw6otgGnHFvtEpJXGFi/7Z36saxo6bpK+v0/rPRI1pPFDfqBcql92ztBJ9pfXV/tEpJWbvP+0H3tbb4/b0vpplnVLqFDU1NTFIvFKJVKsXz58i22d3UNoh3tFyNfF9Hevz9r71/+l2qX0K/lNoXwlltuiSzL4vTTT48jjzyy4r5vetObIsuyeOaZZ/LqHgAAAOgthSxiO/KrvvCLQb/87ltyC7CefPLJiIgurZg/aNCgGDx4cKxYsaJLbV911VVxzTXXdLp92rRpMX369C61VW0t1S4AAACgn0lp7eVCodDx35Tq2pYsengrvgT1hZCN/5VbgNXS0hKDBw+OQYMG5dXkZm0vWbKk0+2tra1RLBZz7xcAAIC+L8XrxSzLkqyrM6Ieqi23AGvo0KHxyiuvxKuvvhoDBgyouO+yZcuitbU1Ro8e3aW2GxsbY+edd+50e0NDQ8fK/QAAALCplK4XC4VCZFkW5XJ5s4W0N0o11CpERG9OuMsjIDMhsLblFmCNGzcuHnjggZg7d2685S1vqbjvLbfcEhEREyZM6FLbp556apx66qmdbm9ubt7q4ncpqhztAQAAkLeUrhc3LuLe3t7epxZx7+0AawtdSbReU5BRYrUtt9uZTZ06Ncrlclx55ZWxevXqTve755574rrrrossy+Kd73xnXt0DAAAAvSXLItuRj678bwfXRHXlNgLrrW99a7zlLW+JP/7xj/GFL3whpk6dGm1tbRERcdddd8XSpUvj/vvvj/nz50e5XI6jjjoq9t9//7y6BwAAAHqJ+IZqy8o53jdy3bp1cfHFF8fdd9+91XRyY1dHHnlkfO5zn4v6+vpc+m1ubs6lnR1hwCnHVruE5BUG5vO5qFVZMbeBkzXJrXDpCb9Zq6xc2o57Z8NrtL+6vtolJK3c5v2h+9rbfH/eltJNs6pdQoeNUwhLpVKfmkL46513i3JCa4lVw7tfXlztEvq13EZgRUQMHDgwvvjFL8a8efNixowZ8dhjj8Xy5cujvb09RowYEePHj49jjjkmDjzwwDy7BQAAAHpRv/81n190Vl1uAVZra2tEbAixJk6cGBMnTsyraQAAAKCK+n1+09/PPwG5BVjTpk2LLMvixz/+cYwePTqvZgEAAIAq27BoerWroD/LLcAaNGhQFItF4RUAAADUmEJElPv1MKT+fO5pyC3AGjNmTLzwwgtRKpWiWCzm1SwAAABQbVk/n0bYn889EbndzuzII4+MUqkU9913X15NAgAAAAno7/lN5m7nVZdbgHXiiSfGuHHj4rLLLouHH344r2YBAACAaitvmEDYXx9UX25TCH/5y1/GpEmT4vnnn4+vf/3rsccee8T48eNj+PDhUSh0npOdcsopeZUAAAAAQA3KLcC69tprI8uyKP91WN0zzzwTzz777DaPE2ABAABA2gpZIcrRvl3HZAmPXSqHKYF9TW4B1n777RdZv17RDQAAAGrThql0tXPNX0vn0l/kFmCdf/75eTUFAAAAJKRX4p7ezJAMsKo5uQVYAAAAQG3Koty3VjPvS7XSJQIsAAAAoKLqLRnUWb+GWPU3uQdY69ati3vuuScWLFgQy5Yti7Vr13Ys7P5aWZbFeeedl3cJAAAAQI4KWRblpIY17eBaUjr1firXAOvhhx+O7373u7Fy5cool8sdCe3GAGvTxHbT7QAAAEDa+vUlfL8++TTkFmAtXrw4zj///Fi7dm3svvvuceCBB8bNN98cgwYNive85z2xYsWKmDdvXrz44osxbNiwOO6446JYLObVPQAAANBL+n1808nMMnac3AKsG264IdauXRsHH3xwnH322VEsFuPmm2+OwYMHxwc/+MGO/W6//fa47LLL4umnn46vfvWreXUPAAAA9JJ+H2AZgVV1hbwamjt3bmRZFqeddlrFkVVTp06ND33oQ/Hggw/Gb37zm7y6BwAAAHpJlhViQ4zVnx9UU24B1ssvvxyFQiH23HPPjteyLIu2trYt9j322GMjy7KYNWtWXt0DAAAAvSSLchQi+u9DflV1uU0hrKuri4EDB262MPugQYOipaUl1q9fH3V1dZu9Pnjw4HjxxRfz6h4AAADoJVnH/0F15DYCa6eddorW1tZob2/veG3nnXeOiIinnnpqs31XrFgRLS0tWx2dBQAAAKSl6iOgEnhQXbn9Hey+++7R3t4ezz33XMdr++67b5TL5fj5z38ea9eujYiI9evXx09+8pOIiBg7dmxe3QMAAAC9pb/fha+/n38CcptC+OY3vznuvffe+MMf/tCxDtbxxx8ft956azz66KPxoQ99KHbbbbdYsmRJrFq1KrIsi3e96115dQ8AAAD0Fnfho8pyC7De9ra3xbJly2LEiBEdr+22227xuc99Li699NJYu3ZtPPnkkxGxYXH397znPXHsscfm1T0AAADQSzasgSXEonpyC7CGDBkS06ZN2+L1o446Kg488MB44IEHorm5ORobG+OAAw6I17/+9Xl1DQAAAPQi2RXVlluAVcmwYcNi8uTJO6IrAAAAIGeZWxBSZTskwAIAAAD6riwiemsZ8yzH4V1li63XLAEWAAAAUFGhEFFu3zGjsLYnz3ptXpVnGLZ5w73TLF0nwAIAAAAqyrIsskLVOv/f569JrHbY2lwWAas6ARYAAABQWZalEeKkUANVIcACAAAAKsqyMI2OqhJgAQAAABX1+4FP/f4NqD4BFgAAAFBRlhUisvZql1E9AqyqE2ABAAAAFWVZOaJai7inQH5VdQIsAAAAoLJUFnGvlv587okQYAEAAAAViW+oNgEWAAAAUFG/vwthfz73RPTnGawAAAAA21YuV7uCfs8ILAAAAKCiDSOwOh+GVAsDlERUaRNgAQAAABUVsqw2UqoKavz0+jwBFgAAAFDRtkZgQW8TYAEAAAAVZYVCRHt7jg3m11Sn8pwTKLurOgEWAAAAUFGWRUShj6U4faxcKnMXQgAAAKAyd+GjyozAAgAAACrKCpnb9FFVAiwAAACgoizCIu5UlQALAAAAqMgILKpNgAUAAABUlGVZ/x6B1Z/PPRECLAAAAKCiQhb9+65+/fncEyHAAgAAACoyAqsfn3siCtUuAAAAAAAqMQILAAAAqCgzhZAqMwILAAAAqKzcXu0KqqvsFozVZgQWAAAAUFFWKESUS9Uug35MgAUAAABUlBUior0L8+j64lS7rgyu6ovnVWNqIsAqFovVLgEAAIBEpXrNmGpdW5NlWe0uQiSc6hNqIsBqamqqdgldttKtN7epfV1btUtIWmFATXzZUiWZz09lvkdXVKiv1Z9a2RGyos9PJWXfnysqtaytdglJ8/1524YneM1YLBb71LXshkXce/6zUjV+2rJ6VW2oiX8ply9fXu0Suqzv5OsAAAC1IaVrxmHDhkWxWIxSqRQrV67cYnuqoVYhsj47UqmPls1r1ESAVSr1nYXkBFgAAAA7VqrXjKnWtXXGMVFdNRFgAQAAAL0nyzLLLVBVAiwAAACgoqyQGYRFVQmwAAAAgG0wAovqEmABAAAAFRUKYQQWVSXAAgAAACrq92tg9edzT4QACwAAAKgoyyKiP2c4/fncEyHAAgAAACoTYFFlAiwAAACgIlMI+/G5J0KABQAAAFQmwKp2Bf2eAAsAAADYhnI/n0bnFozVJsACAAAAKssKEZkQh+opVLsAAAAAIG1ZIYss69+Pnlq6dGl84QtfiL333jsGDx4co0aNimOPPTZuvPHGHrXb1tYWF110URx88MExbNiwGDZsWLzlLW+J733ve9HW1tbpcc8880xceeWV8bnPfS7e/va3x5AhQ7p8rs8880yX3rNf/OIXPTq3TRmBBQAAAFSWRffXgUpp6mGVBpE9+uijMWXKlFiyZElERAwdOjRWrFgRM2bMiBkzZsRZZ50VF1988Xa3u3r16jjmmGNizpw5ERExaNCgiIh44IEH4oEHHojrrrsuZsyYEY2NjVsce+6558YVV1zRg7PaYNSoUVEsFre6bWM9eTACCwAAAKgsy/4aYnXjkZLunkMPzmPdunXxnve8J5YsWRITJ06Mhx56KFauXBkrV66M8847L7Isi0suuSR+9rOfbXfbn/jEJ2LOnDkxYsSIuP7666O1tTVaW1vj+uuvjxEjRsS9994bn/rUp7Z6bKFQiHHjxsXf/d3fxbe//e346le/2q3zu//+++Oll17a6uP444/vVptbYwQWAAAAUFl/vwthD/zoRz+Kp59+OhoaGuI3v/lNjB07NiIiGhoa4uyzz47FixfHpZdeGuecc06ceuqpUV9f36V2586dG9dee21ERPzkJz+JE088sWPbiSeeGKVSKT7wgQ/ElVdeGf/0T/8UEydO3Oz4H//4x5uNnOrpVMbeZgQWAAAAUNGG/GoHrTdV2I5HH1gD66qrroqIiGnTpnWEV5v64he/GFmWxYsvvhizZs3qcrtXX311lMvlGDduXLzvfe/bYvtJJ50U48aNi3K5HNdcc80W2zub9pcqARYAAABQWSHbcY9sOx47sq5uWL16ddx///0REfGud71rq/uMHTs2JkyYEBERt99+e5fbnjlzZkREHHfccVsN2LIsi2OPPXa7202VAAsAAACoqNp3AKz6o5sB1oIFC6Jc3rBy/Gun8G1q47b58+d3qd1yuRwLFizocrsb9+0NJ598cjQ1NcXAgQNjt912i5NOOil+85vf5N6PAAsAAACorFDYsaOdUnt0cwrh4sWLO57vuuuune63cdum+1eyatWqaGlp6XK7q1atitWrV3ep7e11//33R3t7exSLxXjhhRfi+uuvj+OPPz5OPvnkePXVV3PrR4AFAAAAVLY90/pq9dENm4ZGDQ0Nne63cduqVat6pd3tabsrBg0aFJ/61KfizjvvjJUrV8Yrr7wSra2tMW/evDjttNMiIuK6666Lz3zmM7n1KcACAAAAti3rx49uTiGsVbvssktceuml8fa3vz2GDh3a8fp+++0XP//5z+Mf//EfI2LD3REff/zxXPqsy6UVAAAAoHYVslh22NRYfsTkLh/SdO+s2Om+mb1YVPctO3zK9p3LfbNiSDf6GTLkf49qbW2NYcOGbXW/1tbWiIjNwqDtabczm27ratt5+MY3vhH//u//HmvWrIlf//rXsc8++/S4TQEWAAAAUFEWWbQPGhTrhzV1+Zj2QYNia3fHS8F2n8vAwd3qZ9P1qV588cVOA6wXX3wxIiJe97rXdandoUOHxpAhQ2L16tUdx1Zqd+P+O0pjY2Pst99+8cc//jGefvrpXNoUYAEAAACVFSKKr66LupUrunxI8dV1yU692/5zWdutfsaPHx9ZlkW5XI5HH300xo8fv9X9Hn300YiI2HfffbvUbpZlMWHChLj//vs7jq3U7oQJE7az8vQIsAAAAICKskIWI/8wK0b+YdZ2Htg79fTUdp9LN0eSDRkyJA499NCYM2dO/O53v4uTTjppi30WLVoU8+fPj4iIqVOndrntKVOmxP333x+33HJLp/vceuut291uHlpaWjrCsze84Q25tGkRdwAAAGAbylu+VO2F1XvzscXpb+X8u+iDH/xgRERce+218fzzz2+x/dvf/naUy+XYddddY/Lkrq/LNX369MiyLJ544om44YYbtth+/fXXxxNPPBFZlnXUkJfyNt6Pc889N9asWRNZlsXxxx+fS58CLAAAAKCyLNswHXDTR1bDj9eeaw+mQp5xxhmx1157RUtLSxx//PExd+7ciIhYs2ZNfOtb34of/OAHERFx3nnnRX19/WbH7rnnnpFlWXz4wx/eot39998/pk2bFhERH/vYx+Kmm26Kcrkc5XI5brrppvj7v//7iIg47bTTYr/99tvi+La2tmhubu54rFq1qmPbpq83NzdvcezRRx8d559/fsydOzfWr1/f8fr8+fPjox/9aFx44YUddXU2bXJ7mUIIAAAAVJRtDHa266DeqSUX3R9Qtd0GDhwYv/rVr2LKlCkxd+7cOOCAA2LYsGHR0tISpVIpIiLOPPPM+MhHPrLdbf/whz+Mp556KubMmRMnnHBCDB48OMrlcqxdu2HNriOOOCIuu+yyrR579913dzria/To0Zv9+bUjrp599tk4++yz4+yzz466uroYPnx4rFmzZrO7Hk6fPj0uvfTS7T6nzhiBBQAAAFSWZT2fhpeSPKYVbof99tsvHnnkkfj85z8f48aNi3Xr1sXw4cPjmGOOiRtuuCEuueSSbrU7ZMiQ+P3vfx/f/e5346CDDopisRh1dXVx0EEHxUUXXRR33HFHNDY29qz4rfjOd74TZ5xxRrz5zW+OUaNGdYzeGjduXJx22mkxc+bMuPrqq2PAgAG59ZmVtzVxsQ/Y2nC2VA2Ydly1S0hf3/9I9qrCAAMn6b7M56eyRG/znIrMr73ogXJbe7VLSFq55P2ppNTSvbt/wUZtv7i92iV0aGpqimKxGKVSKZYvX77F9lGjRlWhqm1bM31yxF9HC/VXg//7zmqX0K+5kgEAAAAqy6L3f9nXk+aNg6h5AiwAAACgomzjwuapSrg08iHAAgAAACrrziLukCMBFgAAAFBZoS+szE4tE2ABAAAAFWVZISKz0BTV435CAAAAAJWYPll1RmABAAAAlRWyiHI/DnEEWFUnwAIAAAAqSv4uhL1NgFV1AiwAAACgsiz6d4jTn889EQIsAAAAoLL+fhdCAVbVWcQdAAAAqKy/34Cw3N/fgOozAgsAAACoKCtkEe1bGYVUiwOTZFVJEmABAAAAlWXRfxZx7yen2deYQggAAABUZg0oqswILAAAAKCyQiGfdaCqkYOZElgTBFgAAABARVmW9d0phH20bDYnwAIAAAAqK0REeQclQdvbjRFW/YIACwAAAKgs5RFYiZZFvgRYAAAAwDZkFnKnqtyFEAAAAKhMdkWVGYEFAAAAVJYVIjKLTVE9AiwAAACgsqyfTyHsz+eeCAEWAAAAUFmhEP37dn8CrGrLLcBaunRpFAqFGDlyZJf2f/nll6O9vT1Gjx6dVwkAAABAb8iin49C6s/nnobcAqy///u/j6amprj88su7tP+XvvSlaG5ujhtvvDGvEgAAAIDe0N+nEAqwqs4UQgAAAKCy/h5g9edzT0TVAqx169ZFoVCoVvcAAABAV5VDiENVVSVBevHFF2PVqlUxfPjwanQPAAAAbA/hFVXW7RFY9913X8yZM2ez11paWuLiiy+ueFxLS0vMnz8/IiL23XffLvV11VVXxTXXXNPp9mnTpsX06dO71Fa1tVS7AAAAgH6mqamp2iV02DgTqVAoJFXXNmVZWAeKaup2gLVw4cKYOXNmZFkW5fKGW2m++uqrMXPmzC4dP3To0DjllFO6tG9LS0ssWbKk0+2tra1RLBa71BYAAAD9S4rXi1mWJVlXpwRYVFm3A6w3vOENMWXKlI4/z5w5MwYMGBBHHnlkp8dkWRYNDQ0xduzYOOKII2Lo0KFd6quxsTF23nnnTrc3NDREqVTqevEAAAD0GyldLxYKhY6BIO3t7VtsTzbUKmQR7QIsqicrbxw+1UPvfe97o6mpKS6//PI8mtsuzc3NO7zP7how7bhql5C+fD6SNaswwM1D6b7M56cyaztUlLn3Cj1QbtvyIo3/VS55fyoptaytdgn0cW2/uL3aJXRoamqKYrEYpVIpli9fvsX2UaNGVaGqbVv/1dMiejMIzOPnsF6+lqw7v/Oljeh9uV3JfPOb34y6OhdGAAAAUHOyLKKQ+G+z/DKypuWWOE2cODGvpgAAAIDUCIioosTjUwAAAKD6hFdUV65z/kqlUsyYMSPuvvvuePbZZ2P16tVbXZRuUzfeeGOeJQAAAAB5s4g7VZZbgLV27dr42te+Fn/+85+jq+vCZ4YfAgAAQPKyrBCRueEW1ZNbgPXf//3f8fjjj0eWZXHIIYfEYYcdFiNHjowBAwbk1QUAAABQDX1hEfdeZQBOteUWYN1zzz2RZVmcdtppcdJJJ+XVLAAAAFBtWRb9O8Tpz+eehtwCrObm5siyLI4//vi8mgQAAABS0O/XwOrP556G3AKsoUOHxquvvhoDBw7Mq0kAAAAgCdlfR2H1V/353NOQ2wTWSZMmRWtrayxdujSvJgEAAIAUZFk/f1T7L4DcAqyTTz45BgwYEFdccUVeTQIAAABJcAdCqiu3AGv33XePs88+O/70pz/FueeeG4888kisXbs2r+YBAACAaskKCYyCqvKDqurWGlgnnHBCxe0PPfRQPPTQQ11q68Ybb+xOCQAAAMCOkmVhHh3V1K0Aq1zOZ+hgJsEEAACA9AmwqLJuBVjf/OY3864DAAAASFWhENGe8zpYvTmoJaeBN6SjWwHWxIkT864DAAAASFUhixyX0e59ZnzVnG4FWAAAAEB/YiFzqqsPxacAAAAA9Ee5jcCaN2/edu0/YMCAaGxsjF122SWKxWJeZQAAAAB56/eLuPfnc09DbgHW2Wef3a27CtbV1cX+++8fJ554YkyaNCmvcgAAAIC8FLKIsklcVE+ua2CVu7HKf1tbWzzwwAPx4IMPxqmnnhrvf//78ywJAAAA6KmsEBHt1a6Cfiy3AOumm26Ke++9N77//e/HqFGj4oQTToj99tsvdtppp4iIWL58ecybNy9uuummaG5ujjPPPDMmTpwYTz75ZFx//fXx8MMPx1VXXRUTJ06M8ePH51UWAAAA0FP9fgoh1Zbb+L/HHnssvvOd78SECRPioosuiilTpsSYMWOivr4+6uvrY+edd44pU6bERRddFOPHj4/vfOc78dJLL8WBBx4Y3/jGN+Kwww6Lcrkc//M//5NXSQAAAEAeCn+9C2F/fRRMn6y23P4GfvnLX0Z7e3t84hOfiLq6zgd2FYvFOOOMM2L9+vVx3XXXdbw+bdq0iIiYP39+XiUBAAAAuUggRKrmg6rLbQrhY489Fg0NDbHzzjtvc98xY8ZEY2NjLFiwoOO1N7zhDTFgwIBYsWJFXiUBAAAAeTCFkCrLLcBas2ZNlMvlWL9+fcURWBEbFm5fu3ZtFF4zBK+uri7a2y0KBwAAAEnpxk3bIE+5TSEcM2ZMlEqlmDVr1jb3nT17dpRKpRgzZkzHa2vWrInW1tYYPnx4XiUBAAAAeShsHIG1lUe1p/flOlWw0oNqyi3AOuqoo6JcLscPf/jDmDFjRpS3ks6Wy+W47bbb4oc//GFkWRbveMc7OrY98cQTERExduzYvEoCAAAA8pAVNoRYW3tsEQQV+tDjNbV3do4FAVa15TaF8H3ve1/cf//98cQTT8Sll14aV111Veyzzz6x0047RUTE8uXL47HHHotXXnklyuVy7L333nHiiSd2HH/77bdHRMSBBx6YV0kAAABAHgpZRHs3x8CklP1sMdYmpeKoJLcAq76+Pv71X/81fvzjH8fMmTNjxYoVMWfOnMj+ulr/xhFZWZbFlClT4uMf/3jU19d3HP+Rj3wkTj/99Bg2bFheJQEAAAB5yAoRhbzWrN6RodFrEit5VZ+VW4AVETF48OA466yz4u/+7u/ivvvui6effjpeeeWViIgYPnx47LXXXnH44YdvtvbVRiNGjMizFAAAACA3f50a2OdIrGpFrgHWRmPGjIn3vve9vdE0AAAAsKNlmTsRUlW9EmABAAAANaTjDn3V6vuvhGj9lgALAAAAqKyQRZQTmEKYmRLYX3UrwLr44osjImKnnXaK0047bbPXtkeWZXHWWWd1pwQAAABgR8kKEZHXIu6w/boVYM2cOTOyLIvXv/71HQHWxtfKXRjOt3E/ARYAAAD0AVkWEQmMwKLf6laANXny5MiyLJqamrZ4DQAAAKgxhUJEuxFYVE+3AqzPfe5zW7x2xhlnRETEwIEDo1gs9qgoAAAAICFZwQAsqiq3j9+0adNi+vTpsWzZsryaBAAAAJLg7n9UV253IRw0aFAUi8UYPXp0Xk0CAAAAKbBkEFWWW4A1ZsyYeOGFF6JUKplCCAAAALUkK4RRWFRTblMIjzzyyCiVSnHffffl1SQAAACQoqwfPEhKbiOwTjzxxPjDH/4Ql112WQwZMiQOOOCAvJoGAAAAqikrRGSV7kJYC4nPa0aY1cIp1ZDcAqxf/vKXMWnSpHj++efj61//euyxxx4xfvz4GD58eBQKnQ/0OuWUU/IqAQAAAOgNWRa1fxvC3k2sli5dGt/61rfiV7/6VSz6/9m78/C6qnp//O+T0zEd0wksSEEKCG2ZRZEqMsggIqNXCnrBAb0qonidEC/iFXH2WlSus4gIeGVUFAUtyqDMMxSkQIFaoCOd0pY0Ob8/+DXf1qZJ2pz27CSv1/PkaXr22mt9zrBPct5Ze+1ZszJo0KDsueee+dCHPpSjjz56o/ttamrKd77znfzyl7/M448/niTZcccdc9JJJ+W0005L375929xv5syZufnmm3P33Xfn7rvvzr333ptly5YlSSqVzp0uurFjb4xSpbNVdeCoo45KqVRa606WOrHI29VXX93lsefNm9flPjaXflMOrXUJxVedl2SPVdevarkzvVDJ66d9FidtV6mn/87KJlVpau+v9lSaPT7taV62otYl0M01Xf7nWpfQqqGhIeVyOc3NzVm4cOE620eNGlWDqjrWfNk30rU1sIrwe1bXPmuWT/jkRu/78MMP58ADD8ycOXOSJEOGDEljY2Oam5uTJKeffnqmTp26wf0uXbo0Bx98cG6//fYkL19gL0lWrHj5fXPffffNDTfckEGDBq2z7ymnnJKf//znbfbbmaioK2NvjKr9KjphwoRMmDAhEydObP1afVt7XwAAAEDB1ZVe/mPfRn9l7a+60qb/Wmddqy7eh420cuXKvO1tb8ucOXMyceLE3HfffVm8eHEWL16cc889N6VSKeeff35+9rOfbXDfH/jAB3L77bdn+PDhufLKK9PY2JjGxsZceeWVGT58eP7+97/nQx/6UJv71tXVZfz48XnHO96Rr33ta/mv//qvzTb2xqjaDKxaMgOrh+n+L8lNygwsusIMrA6YgdUuM7DoCjOw2mcGVvvMwKKrzMDquuZff6vXf1Yr/9t/btR+3/nOd3L66aenvr4+06dPzzbbbLPW9tNOOy3f+973Mnbs2MycObPTp9098MAD2X333VOpVHL55ZfnuOOOW2v75Zdfnre//e0plUp54IEHMnHixLW2Nzc3p1wut/7/6quvzjHHHJOk4xlYXR17Y/hVFAAAAOhAXddnMHX3r4108cUXJ0mmTJmyTniVJJ/61KdSKpUye/bs3HjjjZ3u95e//GUqlUrGjx+fY489dp3txx13XMaPH59KpZJLLrlkne1rhlcbqqtjbwwBFgAAANC+utQ+QKr110ZYunRp7rzzziTJYYcd1mabbbbZJjvvvHOS5M9/7vxswWnTpiVJDj300LS1BnmpVMohhxyywf0WdWznkgAAAADtK9Wlq4ug90bTp09vPR2vvdPoJk6cmEceeSSPPPJIp/qtVCqZPn16p/pdXUe11GpsARYAAADQvrq6pGK9vg313HPPtX4/duzY9bZbvW3N9u1ZsmRJli1b1ul+lyxZkqVLl2bw4MGd6r+IYwuwAAAAgA6U4oouG27p0qWt39fX16+33eptS5Ys2ST9ru67GgFWrcYWYAEAAADtqys5g5CaEmABAAAAHShlzuAtM3fwKzq9x+ilz2XM0uc3YU0bb2PuS+db/z9rzjpqbGzM0KFD22zX2NiYJBkyZMhG9bs+a27rbN9FHVuABQAAALSvVEpzXZ809enX6V2a6/ps9NX7NrWNui8bYc01ombPnr3eAGv27NlJkle8onMx2ZAhQzJ48OAsXbq0dd/2+l3dvhpqNbYTWAEAAID2lUoppzl9m1/q9Fc5zS+feljAr426Lxvh1a9+dUr/f4j38MMPr7fd6m277LJLJ5+OUnbeeedO97u6bTXUamwzsAAAAIAOjVk2J2OWzdnAvYo5A2vj7suGGzx4cPbZZ5/cfvvt+cMf/pDjjjtunTazZs3KI488kiQ56KCDOt33gQcemDvvvDN//OMf19vm+uuv3+B+izq2GVgAAABA+0p1eTmM+pevUg/9auu+bqSTTjopSXLppZfm2WefXWf71772tVQqlYwdOzYHHHBAp/s98cQTUyqV8vjjj+eqq65aZ/uVV16Zxx9/PKVSqbWGaqnF2D0iwCqXy93mCwAAgM2r1p8D1/eZsFt9Zlzf6Xj/GvzU1XW/r7YCrLbu60Z6//vfn1e96lVZtmxZ3vrWt+aBBx5Ikixfvjxf+cpX8t3vfjdJcu6556Zv375r7bvtttumVCrllFNOWaffXXfdNVOmTEmSvPe9780111yTSqWSSqWSa665Ju973/uSJO9617syYcKEdfZvamrKvHnzWr+WLFnSum3N2+fNm1f1sTdGqVKpuBDmZvTCazp3Pmtv1tziJdmePuViTsEtinK5R+Tym4y3fNh0Wvz8aldTU0utSyi0vn39/GpPnz4en/b48d6xkX9/qNYldHvNf/hJrUuoufJh793ofR9++OEceOCBmTPn5dMWhw4dmmXLlqW5+eW1tT7ykY/k/PPPX2e/bbfdNk8//XROPvnkXHjhhetsX7p0aQ4++ODcfvvtSZKBAwemUqlkxYoVSZJ99903N9xwQwYNGrTOvn/5y186PeOrrc8RXRl7Y/SINbAWLlxY6xIAAAAoqCJ9Zhw6dGjK5XKam5uzePHidbY3NDTUoKrOKCWRlm6sCRMm5MEHH8xXvvKV/Pa3v82zzz6bYcOGZc8998yHP/zhHH300RvV7+DBg3PzzTfnO9/5Tn75y1/mH//4R5Jkzz33zDvf+c6cdtpp68zqqpbNPXaPmIHV1nS2omo+/I21LqHwzMBqnxlY7TMDq3094C0fCssMrPaZgdU+M7DaZwZW+/x471jlt3+pdQmtGhoaWgOstoK1UaNG1aCqjjX/8cIkm+K9fFN8vtk0B0X50Pdskn7pnB4xAwsAAADYhEqldJ9ltP3RvycSYAEAAADtqyvV5gzCUhthlGmHvZIACwAAAGhfqS4pFSQ4aivUoscTYAEAAADtExpRYwIsAAAAoH2lUqwtRS11lxXYAAAAgJoRXlFbZmABAAAA7avVIu7w/xNgAQAAAO0r1UWCRS0JsAAAAID2lUrOIqSmBFgAAABA+8zAosYs4g4AAAB0QHhFbZmBBQAAALSvVJdU1hNilXrQuYXru4/UnAALAAAAaFepVOpZQdX69Ib72E05hRAAAACAQjMDCwAAAGhfVRdx35yznJwS2FMIsAAAAID2bdKrEFYz0PrXGp0S2FMIsAAAAID21bWziHu1bUjmtE5JAqueSoAFAAAAtK9UqnE2VEqbM8DkVb2GAAsAAABo3yY9hbDTRdR4fGpJgAUAAAC0r1SqfX5FrybAAgAAADpWMgOK2hFgAQAAAO0rxCmE9GYCLAAAAKB9Zl9RYwIsAAAAoH11dUnFDCxqR4AFAAAAtK9UchFAakqABQAAALTPGljUWF2tCwAAAACKTnhFbZmBBQAAALSvU4u4d+dzDAV0RSfAAgAAADrQncOpzujp96/7E2ABAAAAHahCwFPLjMgEq25PgAUAAAC0r25TLOK+KROtf6nVBKtuT4AFAAAAtG9zXIWwU+tsrUflX2uTWPU0AiwAAACgXaW6UgodCnUl/KJbEGABAAAA7RMQUWMCLAAAAKADAixqS4AFAAAAtG9zrIEF7RBgAQAAAO1zCiE1JsACAAAA2lcq+CLu9HgCLAAAAKB9ZmBRYwIsAAAAoH11dbWugF5OgAUAAAC0zwwsakyABQAAAHRAgEVtmQMIAAAAQKGZgQUAAAC0zymE1JgACwAAANhEihh8VWpdABtBgAUAAAC0r9STViAqYqhGRwRYAAAAQPucQkiNCbAAAACADgiwqC0BFgAAANA+M7CosZ50EisAAAAAPZAZWAAAAED7TMCixgRYAAAAQAckWNTWJguw5syZk0WLFiVJhg0bljFjxmyqoQAAAIBNyRpY1FhVA6z58+fn17/+dW655ZYsXbp0rW2DBw/OG97whhx//PEZOXJkNYcFAAAANiUBFjVWtQDrgQceyFe+8pU0NjamUqmss33JkiW57rrr8te//jVnnnlmJk2aVK2hAQAAgE1KgEVtVSXAmj9/fs4777wsX748DQ0NOfLII7Pbbru1zrSaP39+7rvvvlx77bVZuHBhvvSlL+V73/uemVgAAADQHZiBRY1VJcC68sors3z58owfPz5f+MIXMnjw4LW2NzQ0ZPz48Tn00EPz+c9/Pk8++WSuuuqqvO9976vG8AAAAAD0YFUJsO65556USqWcdtpp64RXaxoyZEg+/OEP5+Mf/3juvvvuTgdYF198cS655JL1bp8yZUpOPPHEDa67FubVugAAAIBepqGhodYltKqrq2v9t0h1QdFVJcCaO3duBg4cmO22267Dtttvv30GDhyYuXPndrr/ZcuWZc6cOevd3tjYmHK53On+AAAA6D2K+HmxVCoVsq71cwohtVWVAKtPnz5pampKpVJJqYPzYiuVSlatWpU+fTo/9KBBgzJmzJj1bq+vr09zc3On+wMAAKD3KNLnxbq6upRKpVQqlbS0tKyzvbChljWwqLGqBFhjx47Nk08+mbvuuiuvec1r2m171113pampKdtss02n+3/nO9+Zd77znevdPm/evCxcuLDT/QEAANB7FOnzYkNDQ8rlclpaWtqsa9SoUTWoqhMEWNRYXTU62XfffVOpVPK9730vTzzxxHrbzZgxI9/97ndTKpXy+te/vhpDAwAAAJtcyRc1VZUZWG9729vy5z//Oc8991w+8YlPZK+99sqkSZMycuTIJMn8+fPzwAMP5J577klLS0vGjh2bI488shpDAwAAAJtYR8sFwaZWlQCrf//++eIXv5jzzjsvTz75ZO68887cdddda7WpVCpJXl7E/cwzz0z//v2rMTQAAACwyW3mAKszw1U2eRUUSFUCrCQZPXp0vvGNb+SWW27JrbfemhkzZmTx4sVJkqFDh2b8+PGZPHly9ttvv+IuSgcAAACsq4gTsIpYE5tM1QKs5OWrJey///7Zf//9q9ktAAAAUFPSImqrqgEWAAAA0ANZA4sa2+AAa9q0aVUb/MADD6xaXwAAAMAmIsCixjY4wJo6dWrVrj4gwAIAAIDuQIBFbW1wgDV69Oj1blu8eHFWrlyZ5OX1sIYOHdp6e3Nzc5JkwIABGTJkyMbUCgAAANSCGVjU2AYHWD/+8Y/bvP3aa6/NT3/60+y66645/vjjs8suu6Rv375JklWrVuWRRx7Jr3/96zzyyCM55phjcsQRR3StcgAAAAB6haos4n7PPffkxz/+cd7whjfk4x//+DqnGPbp0ye77rprdt1113zrW9/Kj370o4wdOzZ77LFHNYYHAAAANiUTsKixump0ctVVVyVJ3vOe93S4PtYpp5ySJLn66qurMTQAAACwyfX2BKu33//aq8oMrCeffDKDBg1KQ0NDh21HjBiRQYMGZcaMGdUYGgAAANgshDjUTlUCrKampqxatSrLly/PwIED2227fPnyNDY2tq6PBQAAABScRdypsaqcQrj11lunpaUlv/3tbzts+9vf/jYtLS3ZeuutqzE0AAAAsKmVSr6oqaoEWIccckgqlUouueSS/PznP8/ixYvXabNkyZL8/Oc/zyWXXJJSqZRDDz20GkMDAAAA3UKphl90d1U5hfCwww7L/fffn7/97W+56qqrcs011+SVr3xlRo4cmSRZsGBBnnnmmbS0tKRSqWS//fYTYAEAAEB3UarK/JcaEmJ1d1UJsJLkk5/8ZK688spcccUVaWxszMyZMzNz5sy12tTX1+f444/PMcccU61hAQAAAOjhqhZg1dXV5fjjj8+RRx6Ze++9N0888UQWLVqUJBk2bFi233777LHHHunfv3+1hgQAAAA2ixrNYFrfsJXNWgUFULUAa7X+/fvnda97XV73utdVu2sAAACgFoq2iHnBymHTq3qABQAAAPQwffonLU3Z8OSo1O5/22xfaWN6VaXSdohWKqXD6VjrbN7Q6VuVpE58UmueAQAAAKB9/QcmGVjrKujFuvtlBAAAAADo4QRYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaH1qXUA1lMvlWpfQac21LgAAAKCXKepnxqLWBUXUIwKshoaGWpfQaYuHD6x1CYVXqivVuoRiK3l82lWp1LqCQmt5aVWtSyi0UtnE5Ha1OL7a5edXu/o3t9S6hGLz86tdzS/5M3B7Kl4/HSriZ8ZyuVzIuqCoekSAtXDhwlqX0GnydQAAgM2rSJ8Zhw4dmnK5nObm5ixevHid7UItaFuPCLCam7vPX2QEWAAAAJtXUT8zFrUuKCLnSgAAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhVa1AGvq1Kn5yU9+0un2P/vZz3L++edXa3gAAAAAeqiqBVjTpk3LzTff3On2t956a6ZNm1at4QEAAADooZxCCAAAAECh1STAamlpyYsvvpj+/fvXYngAAAAAupE+G7tjY2Njli1bttZtzc3NmTt37nr3qVQqWbZsWaZNm5ampqZss802Gzs8AAAAAL3ERgdY11xzTX71q1+tdduSJUty6qmndmr/UqmU/fffv1NtL7744lxyySXr3T5lypSceOKJneqr1pZ13AQAAIAqamhoqHUJrerq6lr/LVJdUHQbHWAlL8+oWq1UKq31//aMHDkyhxxySI466qhOtV+2bFnmzJmz3u2NjY0pl8ud6gsAAIDepYifF0ulUiHrgqLa6ADrbW97Ww466KAkLwdZ73//+zN06NB885vfXO8+pVIp9fX1GTRo0AaNNWjQoIwZM2a92+vr69Pc3LxBfQIAANA7FOnzYl1dXesEkJaWlnW2C7WgbRsdYA0aNGitIGrChAkZOnRou0HTxnrnO9+Zd77znevdPm/evCxcuLDq424K/WpdAAAAQC9TpM+LDQ0NKZfLaWlpabOuUaNG1aAqKL4unUK4pvPOO69aXQEAAABAq6oFWG2ZM2dOFi1alCQZNmzYJpmdBQAAAEDPVvUAa/78+fn1r3+dW265JUuXLl1r2+DBg/OGN7whxx9/fEaOHFntoQEAAADogeqq2dkDDzyQj3zkI/nDH/6QJUuWpFKprPW1ZMmSXHfddfnIRz6SBx98sJpDAwAAANBDVW0G1vz583Peeedl+fLlaWhoyJFHHpnddtutdabV/Pnzc9999+Xaa6/NwoUL86UvfSnf+973zMQCAAAAoF1VC7CuvPLKLF++POPHj88XvvCFDB48eK3tDQ0NGT9+fA499NB8/vOfz5NPPpmrrroq73vf+6pVAgAAAAA9UNVOIbznnntSKpVy2mmnrRNerWnIkCH58Ic/nEqlkrvvvrtawwMAAADQQ1UtwJo7d24GDhyY7bbbrsO222+/fQYOHJi5c+dWa3gAAAAAeqiqBVh9+vRJU1NTKpVKh20rlUpWrVqVPn2qfhFEAAAAAHqYqgVYY8eOzapVq3LXXXd12Pauu+5KU1NTxo4dW63hAQAAAOihqhZg7bvvvqlUKvne976XJ554Yr3tZsyYke9+97splUp5/etfX63hAQAAAOihqnYO39ve9rb8+c9/znPPPZdPfOIT2WuvvTJp0qSMHDkySTJ//vw88MADueeee9LS0pKxY8fmyCOPrNbwAAAAAPRQVQuw+vfvny9+8Ys577zz8uSTT+bOO+9c53TC1etjbb/99jnzzDPTv3//ag0PAAAAQA9V1VXUR48enW984xu55ZZbcuutt2bGjBlZvHhxkmTo0KEZP358Jk+enP322y/lcrmaQwMAAADQQ1X9MoDlcjn7779/9t9//2p3DQAAAEAvVLVF3AEAAABgU6j6DKxKpZLp06fn6aefztKlS9Pc3Nxu+xNOOKHaJQAAAADQg1Q1wLrjjjvy/e9/PwsWLOj0PgIsAAAAANpTtQDrwQcfzJe//OW0tLQkSUaOHJmRI0emX79+1RoCAAAAgF6oagHWr3/967S0tGTcuHH56Ec/mu23375aXQMAAADQi1UtwHr88cdTKpXyn//5nxk3bly1ugUAAACgl6vaVQibm5szYMAA4RUAAAAAVVW1AGvs2LFpamrq8KqDAAAAALAhqhZgHXzwwVm1alVuv/32anUJAAAAANULsI444ojstddeueCCC/Loo49Wq1sAAAAAermqLeL+q1/9Kttvv30ee+yxfOYzn8kuu+ySHXbYIQMHDmx3vxNOOKFaJQAAAADQA1UtwLr00ktTKpWSJJVKJQ8//HAeeeSRDvcTYAEAAADQnqoFWBMmTGgNsAAAAACgWqoWYJ133nnV6goAAAAAWlVtEXcAAAAA2BQEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaH1qXUA1lMvlWpcAAABAQRX1M2NR64Ii6hEBVkNDQ61L6LTGYQNrXULxVSq1rqDQSmUTJ9tVKtW6gkIr1/evdQmF1ty4stYlFFplVXOtS6AbqzT7+c7G6xEfWjahUtnvPx2pL+BnxnK53K0+y0Kt9YifBQsXLqx1CZ3moyMAAMDmVaTPjEOHDk25XE5zc3MWL168znahFrStRwRYzc3+IgwAAEDbivqZsah1QRE5FwkAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoND6bMxODz30UNUKmDhxYtX6AgAAAKDn2agA66yzzkqpVKpKAVdffXVV+gEAAACgZ9qoACtJKpVKNesAAAAAgDZtVIB1zTXXVLuOdl188cW55JJL1rt9ypQpOfHEEzdjRRtvZa0LAAAA6GUaGhpqXUKrurq61n+LVBcU3UbPwNqcli1bljlz5qx3e2NjY8rl8masCAAAgO6iiJ8XS6VSIeuCouoWAdagQYMyZsyY9W6vr69Pc3PzZqwIAACA7qJInxfr6upSKpVSqVTS0tKyznahFrStVOkBi1nNmzev1iV0Wv1/HF3rEoqv+78kN6lSua7WJRRblS4w0VOV6/vXuoRCa250ond7KquK88s/3U+l2c932FRKZb//dKTxB5t3GZz2NDQ0pFwup7m5OQsXLlxn+6hRo2pQFRTfRs3Auuyyy6pWwAknnFC1vgAAAADoeTYqwLr00ktTqtIsBwEWAAAAAO3ZqABrwoQJVQuwAAAAAKA9GxVgnXfeedWuAwAAAADaZDVoAAAAAApNgAUAAABAoQmwAAAAACi0jVoD66yzzkqSjBkzJh/96EfXum1DlEqlnHvuuRtTAgAAAAC9xEYFWA899FCSZOutt17ntg3hSoYAAAAAdGSjAqwTTjghSTJ06NB1bgMAAACAatqoAGvKlCmdug0AAAAAuqpqi7jfdtttG9S+Uqnk/PPPr9bwAAAAAPRQVQuwvvGNb2zQOlhTp07NtGnTqjU8AAAAAD1U1QKspqamfOlLX8oTTzzRbrtKpZL/+Z//yY033ph+/fpVa3gAAAAAeqiqBVj/9m//lsbGxpxzzjn55z//2WabSqWSb33rW/nLX/6S/v3756yzzqrW8AAAAAD0UFULsE466aQcdthhWbx4cT7/+c9n3rx5a21vaWnJN77xjdx0000ZMGBAPve5z2W33Xar1vAAAAAA9FBVC7CS5D/+4z8yefLkzJ07N2effXYWL16cJGlubs7Xv/713HLLLRkwYED+67/+K7vuums1hwYAAACgh6pqgFUqlfLxj388e+yxR/75z3/mnHPOyZIlS/LVr341f/vb3zJw4MCcffbZmThxYjWHBQAAAKAHq2qAlSTlcjlnnnlmdtpppzzxxBN5//vfn9tvv701vJowYUK1hwQAAACgB6t6gJUk/fv3z9lnn51tttkmjY2Nqa+vzznnnJNddtllUwwHAAAAQA/WZ2N2uuyyyzrVbuedd84zzzyTCRMm5L777st99923TpsTTjhhY0oAAAAAoJfYqADr0ksvTalU6nT7u+66K3fddVeb2wRYAAAAALRnowKsCRMmbFCABQAAAAAba6MCrPPOO6/adQAAAABAmzbJIu4AAAAAUC0CLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACq1PrQuohnK5XOsSAAAAKKiifmYsal1QRD0iwGpoaKh1CZ22aP7SWpdAN1cqlWpdQqFVKpVal0A3VlnVXOsS6Ma8P7dvVVNLrUuAHqulxe8/HRldwM+M5XK5W32WhVrrEQHWwoULa11CpzlnEwAAYPMq0mfGoUOHplwup7m5OYsXL15nu1AL2tYjAqzm5u7zF3MBFgAAwOZV1M+MRa0LikieAgAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKLQNDrDOOuusfOUrX1nrtrlz52b+/PlVKwoAAAAAVuuzoTs89NBDaWhoWOu2973vfWloaMiFF15YrboAAAAAIMlGzMCqq6tLU1PTpqgFAAAAANaxwQHWsGHDsmzZsjz//POboh4AAAAAWMsGn0I4adKk3HTTTfnEJz6RSZMmZcCAAUmSZcuWZerUqZ3up1Qq5fTTT9/Q4QEAAADoZTY4wDrppJPywAMP5MUXX8zf/va31ttfeumlTJs2rcP9S6VSKpWKAAsAAACATtngAGvLLbfM9773vdx000155plnsnLlykybNi39+vXL5MmTN0WNAAAAAPRiGxxgJcngwYPzlre8pfX/06ZNy6BBg/LRj360aoUBAAAAQLKRAda/mjBhQoYOHVqNrtp08cUX55JLLlnv9ilTpuTEE0/cZONX09JaFwAAANDLNDQ01LqEVnV1da3/FqkuKLqqBFjnnXdeNbpZr2XLlmXOnDnr3d7Y2JhyubxJawAAAKB7KuLnxVKpVMi6oKiqEmBtaoMGDcqYMWPWu72+vj7Nzc2bsSIAAAC6iyJ9Xqyrq2u9uFlLS8s624Va0LZSpVKpbMgOl112WdUGP+GEE6rSz7x586rSz+bQ9+0H17oEurlSqVTrEgptA9/SYC2VVcX55Zbux/tz+1Y1rfshDaiOlha//3Sk9Lu/1rqEVg0NDSmXy2lubs7ChQvX2T5q1KgaVAXFt8EzsC699NKq/YJWrQALAAAAgJ5rgwOsCRMm+AsjAAAAAJvNBgdYm3rBdgAAAABYU12tCwAAAACA9giwAAAAACi0DT6FsCO33XZb7r333sydOzcvvfRSzj333NZtK1asyFNPPZVSqZRXv/rV1R4aAAAAgB6oagHW888/ny9/+ct5+umnk7x8Kft/Xey9b9+++da3vpW5c+fmK1/5ihALAAAAgA5V5RTCxsbGnH322Zk5c2aGDx+egw46KAMGDFinXblczqGHHppKpZK///3v1RgaAAAAgB6uKgHWb37zm7zwwgvZYYcd8t3vfjcf+chH2gywkuS1r31tkmT69OnVGBoAAACAHq4qAdbf//73lEqlvO9978vgwYPbbbv11lunXC5n9uzZ1RgaAAAAgB6uKgHW888/n3K5nB133LHDtqVSKfX19WlsbKzG0AAAAAD0cFUJsFpaWtKnT5/U1XXcXaVSyYoVK9K/f/9qDA0AAABAD1eVAGvUqFFZuXJlXnzxxQ7b/uMf/0hTU1O23HLLagwNAAAAQA9XlQBr0qRJSZIbbrih3XaVSiW//OUvUyqVsueee1ZjaAAAAAB6uKoEWEcffXTq6upy+eWX5/bbb2+zzfPPP5/zzjsv999/f/r165cjjjiiGkMDAAAA0MOVKpVKpRodXX/99bnggguSJFtuuWXmzZuXVatWZY899sjcuXMza9as1rb/+Z//mTe84Q3VGDZJMm/evKr1tan1ffvBtS6Bbq5UKtW6hEKr0lsavVRlVXOtS6Ab8/7cvlVNLbUuAXqslha//3Sk9Lu/1rqEVg0NDSmXy2lubs7ChQvX2T5q1KgaVAXF16daHR1yyCEZMWJEfvjDH+a5555rvf2ee+5p/X706NH54Ac/mL322qtawwIAAADQw1UtwEqSvffeO3vuuWceeuihPProo1mwYEFaWloyfPjw7Lzzztl1111TLperOSQAAAAAPVxVA6wkqaury6677ppdd9212l0DAAAA0AtVZRF3AAAAANhUqjYDq6WlJaVSqc0FTK+77ro89NBDaWpqyl577ZVDDjnEQqcAAAAAdEpVAqzVVyCcPHlyPvGJT6y17dxzz81dd92V5OWrg91xxx255557cuaZZ1ZjaAAAAAB6uKqcQrj6SoMHHHDAWrfffffdufPOO1OpVLL33ntnv/32S6lUyu23355bbrmlGkMDAAAA0MNVZQbW008/nSTZaaed1rr9xhtvTKlUylFHHZV3v/vdSZJrr702P/rRjzJt2rRMnjy5GsMDAAAA0INVZQbWokWL0r9//wwePHit2++///4kyWGHHdZ620EHHZQkefLJJ6sxNAAAAAA9XFUCrBUrVqxz2/PPP5/Fixdn1KhRecUrXtF6+8CBAzNo0KAsXry4GkMDAAAA0MNVJcAaOnRoVq5cuVYodd999yVJdt5553XaNzc3Z+DAgdUYGgAAAIAerioB1vbbb58kueaaa5IkK1euzHXXXZdSqZTdd999rbYLFy7MihUr0tDQUI2hAQAAAOjhqrKI+2GHHZa77rorV1xxRW677bY0NjZmwYIFGTJkSF7/+tev1fbBBx9MkowbN64aQwMAAADQw1VlBtZrXvOa/Nu//VuSZNasWVmwYEEGDx6cM844Y51TBf/6178mSXbddddqDA0AAABAD1eVGVhJctJJJ+XNb35z/vGPf6S+vj477rjjOlclXLVqVXbYYYeMHz8+++yzT7WGBgAAAKAHq0qA1djYmCQZOXJkJk+evP7B+vTJCSecUI0hAQAAAOglqnIK4ZQpU3LiiSdmwYIF1egOAAAAAFpVZQbWgAEDUi6XM3r06Gp0BwAAAACtqjIDa4sttsjKlSvT3Nxcje4AAAAAoFVVAqzJkyenubk5t912WzW6AwAAAIBWVQmwjjnmmIwfPz4XXHBB7r///mp0CQAAAABJqrQG1hVXXJFJkybl2Wefzec///mMGzcur371qzNs2LDU1a0/I3NFQgAAAAA6UpUA69JLL02pVEqlUkmSzJw5M08//XSH+wmwAAAAAOhIVQKsCRMmpFQqVaMrAAAAAFhLVQKs8847rxrdAAAAAMA6qrKIOwAAAABsKgIsAAAAAApNgAUAAABAoVVlDayzzjprg/cplUo599xzqzE8AAAAAD1YVQKshx56qFPtVl+psFKpuGohAAAAAJ1SlQDrhBNOaHd7Y2NjHn/88UyfPj2DBw/O4YcfnnK5XI2hAQAAAOjhqhJgTZkypVPtHn744Zx33nmZOXNmPve5z1VjaAAAAAB6uM26iPuECRPywQ9+MHfddVeuvfbazTk0AAAAAN3UZr8K4b777ptyuZwbbrhhcw8NAAAAQDe02QOscrmcPn365LnnntvcQwMAAADQDW32AOvpp5/OihUrLOIOAAAAQKdUZRH3znriiScyderUlEql7LjjjptzaAAAAAC6qaoEWGeddVa725uamjJv3rwsWLAglUol5XI5//Zv/1aNoQEAAADo4aoSYD300EOdbjty5Mh88IMfzIQJE6oxNAAAAAA9XFUCrBNOOKHd7eVyOYMHD864ceOy8847p65usy+9BQAAAEA3VZUAa8qUKdXoBgAAAADWsVkXcd9UXNEQAACA9SnqZ8ai1gVF1CMCrIaGhlqX0GnzljfVuoTC6zugR7wsN50+fsi1p67sFGU2Xqm+f61LoBurNLfUuoRCG9DPz/f21A3sW+sSiq2uVOsKis37T4cGFvAzY7lc7lafZaHWqvqbREtLS/72t7/llltuyYwZM7Jo0aIkybBhwzJ+/Pi88Y1vzL777ptSqbo/gBYuXFjV/gAAAOg5ivSZcejQoSmXy2lubs7ixYvX2S7UgrZVLcCaP39+vvzlL2fGjBlJkkql0rpt7ty5mTt3bm677bbssMMO+cxnPpORI0dWa+g0NzdXrS8AAAB6lqJ+ZixqXVBEVQmwVq5cmbPPPjuzZs1KqVTK7rvvnt122y2jRo1KksybNy/3339/7rvvvjz++OM5++yz8z//8z/p169fNYYHAAAAoAerSoB17bXXZtasWRk2bFjOPPPM7Lzzzuu0OeaYY/LII4/ky1/+cv75z3/m2muvzbHHHluN4QEAAADowaqy2vGtt96aUqmUD3/4w22GV6vtsssu+fCHP5xKpZJbbrmlGkMDAAAA0MNVJcCaPXt2+vTpk3322afDtvvss0/69u2b2bNnV2NoAAAAAHq4qgRYq1atSt++fTt1dcG6urr07ds3q1atqsbQAAAAAPRwVQmwRo8eneXLl2fmzJkdtn3qqafS2NiY0aNHV2NoAAAAAHq4qgRYu+++eyqVSi644II0Njaut93y5ctzwQUXpFQqZY899qjG0AAAAAD0cFW5CuGxxx6badOm5R//+EdOO+20HHXUUZk0aVJGjhyZJJk/f37uv//+XHvttZk3b14GDBjgCoQAAAAAdEpVAqzRo0fnM5/5TL761a9m/vz5+dnPftZmu0qlkoEDB+bTn/50Ro0aVY2hAQAAAOjhqnIKYZLsscceOf/88/PmN785gwYNSqVSWetr0KBBOfTQQ/Od73zH6YMAAAAAdFqpUqlUNkXHzz//fBYtWpQkGTZsWLbccstNMUySZN68eZus76p76/61rqDw+g6oysTAHqvU1+PTnlK5ark8vZDXD11RaW6pdQmFVtfPz6/21A3sW+sSiq2u46ud92refzq07IKral1Cq4aGhpTL5TQ3N2fhwoXrbHe2ErStKr9JXHPNNTnwwAMzZMiQ1tu23HLLTRpaAQAAANA7VOVPzT/96U/z7ne/O1//+tdz7733VqNLAAAAAEhSpRlYW2yxRV544YXccsstufXWWzNq1KgcfPDBOfjgg01/BAAAAKBLqrYG1oMPPpjrr78+f//739PU1JRSqZRSqZTdd989b37zm/Pa17425XK5GkOtwxpYPYs1sNpnDaz2WcOIrvD6oSusgdU+a2C1zxpYHbAGVvu8/3TIGljQ/VXtN4lJkyZl0qRJWbZsWf7617/mT3/6U5544oncc889uffeezNkyJAceOCBOfjgg/PKV76yWsMCAAAA0MNtsqsQJslTTz2V66+/PjfddFOWLl2aUunlv5zsuOOOOeSQQ/KGN7wh/fv37/I4ZmD1LGZgtc8MrPaZQUNXeP3QFWZgtc8MrPaZgdUBM7Da5/2nQ2ZgQfe3SQOs1ZqamvL3v/89v/nNb/L444+3BlkDBgzIG9/4xhx55JFdmpUlwOpZBFjtE2C1TwBBV3j90BUCrPYJsNonwOqAAKt93n86JMCC7m+z/Kb+8MMP5/bbb8/MmTOTJKszs+XLl+f666/P6aefnu9///tpbm7eHOUAAAAA0I1ssj+FzZ07N3/605/y5z//OfPmzWsNrXbZZZcceuihed3rXpcHH3ww1113Xe6+++784Q9/yNChQ3PiiSduqpIAAAAA6IaqGmA1NTXltttuy5/+9Kfcf//9SV6ebTVkyJAccMABOfTQQ7P11lu3tn/Na16T17zmNbnpppvyzW9+MzfeeKMACwAAAIC1VCXAeuqpp/KnP/0pf/nLX7Js2bLW2VYTJ07MoYcemn333Td9+67/vP43vvGN+eEPf9i91rICAAAAYLOoSoD1sY99LKVSKZVKJUOHDs1BBx2UQw45JGPHju10HwMGDMjSpUurUQ4AAAAAPUjVTiGcNGlS69pWffpseLdf/epXLeIOAAAAwDqqEmD94Ac/yJZbbtmlPkaOHFmNUgAAAADoYeqq0UlXwysAAAAAWJ+qBFgAAAAAsKkIsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIVWtQBr7ty5mT9/fqfbz58/P3Pnzq3W8AAAAAD0UH2q1dH73ve+NDQ05MILL+xU+09/+tOZN29err766mqVAAAAAEAP5BRCAAAAAAqtZgHWypUrU1cnPwMAAACgfTVJkGbPnp0lS5Zk2LBhtRgeAAAAgG5ko9fAuu2223L77bevdduyZcsyderUdvdbtmxZHnnkkSTJLrvs0qmxLr744lxyySXr3T5lypSceOKJneqr1hbWugAAAIBepqGhodYltFp9JlJdXV2h6oKi2+gA66mnnsq0adNSKpVSqVSSJC+99FKmTZvWqf2HDBmSE044oVNtly1bljlz5qx3e2NjY8rlcqf6AgAAoHcp4ufFUqlUyLqgqDY6wNpuu+1y4IEHtv5/2rRp6devXyZPnrzefUqlUurr67PNNttk3333zZAhQzo11qBBgzJmzJj1bq+vr09zc3PniwcAAKDXKNLnxbq6utaJIC0tLetsF2pB20qV1dOnuuioo45KQ0NDLrzwwmp0t0HmzZu32cfcaG/dv9YVFF7fARudq/YKpb4en/aUyi4Owcbz+qErKs3rfgjh/6nr5+dXe+oG9q11CcVWV6p1BcXm/adDyy64qtYltGpoaEi5XE5zc3MWLlx3kZlRo0bVoCoovqr9JvGlL30pffr4xQQAAACA6qpa4jRx4sRqdQUAAAAArZwrAQAAAEChVW0G1qmnnrrB+5RKpfzwhz+sVgkAAAAA9EBVC7DmzJnTqXarr7aw+nsAAAAAaE/VAqzTTz+93e2NjY15/PHH87e//S39+/fPiSeemAEDBlRreAAAAAB6qKoFWAcddFCn2p1wwgn5/Oc/nxtvvDFf/vKXqzU8AAAAAD3UZl/EfezYsfnQhz6Uxx9/PFdcccXmHh4AAACAbqYmVyHcfffd07dv39x00021GB4AAACAbqQmAVaS1NXVdXrhdwAAAAB6r5oEWNOnT8/KlSst4g4AAABAh6q2iHtnNDc354477shPfvKTlEqlTJgwYXMODwAAAEA3VLUA69RTT213e1NTU1588cUkSaVSyYABAzJlypRqDQ8AAABAD1W1AGtD1rPaaaedcuqpp2bbbbet1vAAAAAA9FBVC7BOP/30dreXy+UMHjw448aNy+jRo6s1LAAAAAA9XNUCrIMOOqhaXQEAAABAq026iPvSpUuzePHiJMnQoUMzePDgTTkcAAAAAD1Q1QOsF198Mddcc01uvfXWddbFGjNmTPbbb78cddRRGT58eLWHBgAAAKAHqmqAdd999+XrX/96li1blkqlss72F154IVdddVWuv/76fPKTn8zuu+9ezeEBAAAA6IGqFmA9++yzOffcc9PU1JShQ4fm8MMPz8SJEzNy5MgkyYIFC/LQQw/lD3/4Q1588cWce+65+Z//+Z+88pWvrFYJAAAAAPRAVQuwLr300jQ1NWWHHXbIOeecs856V1tttVUmTZqUI488Muecc04ef/zxXHbZZfnkJz9ZrRIAAAAA6IHqqtXRgw8+mFKplI985CPtLtY+ePDgnHbaaUmSBx54oFrDAwAAANBDVS3AWr58eQYOHJhx48Z12HbbbbdNfX19VqxYUa3hAQAAAOihqhZgbbHFFmlqakpzc3OHbZubm9PU1JQxY8ZUa3gAAAAAeqiqBViTJ0/OqlWrcvPNN3fY9uabb05TU1Pe8IY3VGt4AAAAAHqoqgVYxx9/fHbcccf87//+b2666ab1trv55pvzv//7v9lpp51y3HHHVWt4AAAAAHqoUqVSqWzoTpdddlmbt7/00ku57rrrsnz58owePToTJ07MyJEjkyTz58/Pww8/nDlz5qS+vj6HH354+vbtmxNOOKFr9yDJvHnzutzHZvPW/WtdQeH1HVC1i2P2SKW+Hp/2lMpVy+Xphbx+6IpKc0utSyi0un5+frWnbmDfWpdQbHWlWldQbN5/OrTsgqtqXUKrhoaGlMvlNDc3Z+HChetsHzVqVA2qguLbqN8kLr300pRK6/8hUqlUMmfOnNx4443r3J4kjY2NueKKK5KkKgEWAAAAAD3XRgVYEyZMaDfAAgAAAIBq2agA67zzzqt2HQAAAADQJot9AAAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKLQ+tS6gGsrlcq1L6LTmWhcAAADQyxT1M2NR64IiKlUqlUqtiwAAAACA9ekRM7AWLlxY6xK6paFDh6ZcLqe5uTmLFy+udTl0QrlcztChQ7N48eI0N5vPV3SOse7F8dW9OL66F8dX9+L46l4cX91PR8dYQ0NDDaqC4usRAZY36q7zGHYvzc3NnrNuxvPVfTi+uh/PV/fh+Op+PF/dh+Ore/KcQedZxB0AAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKDQBFgAAAACFJsACAAAAoNAEWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACq1PVztYunRpnnjiidTX12eHHXZYa9vChQvz4x//OA8++GCampqy99575z3veU8aGhq6OiwAAAAAvUSXA6w//vGP+cUvfpG3vvWtawVYTU1NOfPMM/P888+nUqkkSW6++eY8+eST+Z//+Z/069evq0MDAAAA0At0+RTC++67L0my//77r3X7jTfemOeeey4DBw7Mu9/97nzgAx/IsGHD8s9//jO///3vuzosAAAAAL1ElwOs559/PkmyzTbbrHX7rbfemlKplHe96105+uij85a3vCUf+chHUqlU8ve//72rwwIAAADQS3Q5wFq0aFHq6+vTv3//1ttaWloyffr0JMkb3vCG1tv32GOPlEqlzJo1q6vDAgAAANBLdDnAamlpyUsvvbTWbU899VRWrlyZcePGZciQIa23l8vlDBo0KMuXL+/qsAAAAAD0El0OsEaMGJFVq1Zl9uzZrbfdeeedSZKdd955nfYrVqzI0KFDuzosAAAAAL1El69COGHChLzwwgv56U9/mo985CNZsGBBfv/736dUKmWvvfZaq+3s2bOzatWqjBgxYoPGuPjii3PJJZesd/uUKVNy4oknblT9vVldXV3rvw0NDTWuhs4olUpJkmHDhrVe3ZPicox1L46v7sXx1b04vroXx1f34vjqfhxjsHG6HGAdffTRuemmm3LXXXfl5JNPTpJUKpVss8022Xvvvddqe8899yRJxo8fv0FjLFu2LHPmzFnv9sbGxpTL5Q2snNVKpZLHr5tZ/UOP7sEx1r04vroXx1f34vjqXhxf3Yvjq/txjMGG6XKANW7cuHz2s5/ND37wg7zwwgsplUqZNGlSTjvttNa/Bqx2ww03JEl22223DRpj0KBBGTNmzHq319fXp7m5ecOL7+Xq6upSKpVSqVTS0tJS63LohFKplLq6urS0tPgLWzfgGOteHF/di+Ore3F8dS+Or+7F8dX9dHSMCbWgbaVKFd/lFi1alAEDBqx1RcLVVq1alUcffTRJssMOO7TZZmPNmzevan31Jg0NDSmXy2lubs7ChQtrXQ6dUC6X09DQkIULFwptuwHHWPfi+OpeHF/di+Ore3F8dS+Or+6no2Ns1KhRNagKiq/LM7DWNGzYsPUP1KdPJk6cWM3hAAAAAOgFnCgNAAAAQKF1eQbW3LlzN2q/0aNHd3VoAAAAAHqBLgdYp5566kbtd/XVV3d1aAAAAAB6gS4HWK50AQAAAMCm1OUA60c/+lG725ctW5bHH388v/3tb7NgwYJ87GMfy7hx47o6LAAAAAC9RJcDrDFjxnTYZrvttssBBxyQL3zhCzn//PPz7W9/u6vDAgAAANBLbLarEPbt2zfvf//7s3jx4lx22WWba1gAAAAAurnNFmAlyTbbbJP6+vrcfffdm3NYAAAAALqxLp9CuCGampqycuXKvPTSS5tzWAAAAAC6sc06A+umm25Kc3Nzhg8fvjmHBQAAAKAb6/IMrLlz57a7/aWXXsq8efNyxx135I9//GNKpVL22Wefrg4LAAAAQC/R5QDr1FNP7XTbSqWSsWPHZsqUKV0dFgAAAIBeossBVqVS6VS7LbbYIpMnT87xxx+f+vr6rg4LAAAAQC/R5QDrRz/6Ubvby+VyBg8enP79+3d1KAAAAAB6oS4HWGPGjKlGHQAAAADQps16FUIAAAAA2FBdnoHVkWeeeSYPP/xwmpqasscee+SVr3zlph4SAAAAgB6kywHWvffem1/96lfZeeedc/LJJ6+17corr8wvfvGL1oXeS6VSTj755Bx99NFdHRYAAACAXqLLpxDeeuutefTRR7P11luvdfvMmTNz0UUXpaWlJYMHD87QoUPT0tKSCy+8MI899lhXhwUAAACgl+hygLU6jNpjjz3Wuv36669PpVLJ3nvvnQsvvDAXXXRR3vzmN6dSqeT3v/99V4cFAAAAoJfocoD14osvplwuZ8SIEWvdfu+996ZUKuXtb397+vR5+UzFKVOmJEmmT5/e1WEBAAAA6CW6HGAtW7YsAwYMWOu2xYsXZ/bs2Rk0aFBe/epXt94+cuTIDBgwIAsWLOjqsAAAAAD0El0OsAYMGJBly5alqamp9bYHH3wwSbLzzjuv075cLqdcLnd1WAAAAAB6iS4HWNtss02SlxdzX+3GG29MqVTKhAkT1mq7fPnyNDY2pqGhoavDAgAAANBL9OlqB5MnT8706dNzwQUXZPr06Vm4cGHuvPPOlMvlTJ48ea22jz32WCqVSl7xild0dVgAAAAAeokuB1iHH354/v73v+ehhx7KH//4x1QqlSTJCSeckNGjR6/V9pZbbkmpVMrEiRO7OiwAAAAAvUSXA6xyuZz//u//zk033ZTHHnssAwcOzF577bVOSLVq1aosWLAgEyZMyN57793VYQEAAADoJbocYCUvh1gHHHBADjjggPUP1KdPzj777GoMBwAAAEAv0uVF3AEAAABgU6rKDKzVnnzyydx7772ZO3duXnrppZx++umt21atWpVFixalVCplxIgR1RwWAAAAgB6sKgHWkiVLMnXq1Nx1111JkkqlklKptFaA1dzcnDPOOCOLFy/O1KlTM27cuGoMDQAAAEAP1+VTCJuamvL5z38+d911V/r165dJkyalb9++67Tr379/DjnkkFQqldx6661dHRYAAACAXqLLAdZ1112XJ554Iq94xSty/vnn54tf/GIGDRrUZtt99903SfLwww93dVgAAAAAeokuB1g333xzSqVS3v/+92fLLbdst+22226burq6zJo1q6vDAgAAANBLdDnAmjVrVurq6rLrrrt22LZcLqe+vj5Llizp6rAAAAAA9BJVWQOrf//+KZfLnWr/0ksvpV+/fl0dFgAAAIBeossB1vDhw7N8+fIsXbq0w7ZPP/10XnrppYwePbqrwwIAAADQS3Q5wJowYUKS5Kabbuqw7a9//euUSqVOnW4IAAAAAEkVAqy3ve1tSZJLL700M2bMaLPN8uXL84Mf/CA333xz6urqcsQRR3R1WAAAAAB6iT5d7WD77bfPO97xjlx22WX59Kc/nQkTJmT58uVJkv/93//N3Llz88gjj2TFihVJkpNPPjljx47t6rAAAAAA9BJdDrCSZMqUKRk2bFh+8Ytf5P7772+9/Y9//GMqlUqSZODAgTnllFNy2GGHVWNIAAAAAHqJqgRYSfKWt7wlb3rTm/K3v/0tjz76aBYsWJCWlpYMHz48r371qzN58uQMHjy4WsMBAAAA0EtULcBKkvr6+hx88ME5+OCDq9ktAAAAAL1YlxdxBwAAAIBNaYNmYE2dOjVJMmLEiLzrXe9a67YN1bdv3wwfPjw77bRT9thjj9TVydIAAAAAWNcGBVjTpk1LqVTKVltt1Rpgrb5t9WLtnVUqlVq/33bbbfOFL3whw4YN26A+AAAAAOj5NijAOuCAA1IqldLQ0LDObRuqubk5CxYsyKOPPpqZM2fmF7/4RU477bQN7gcAAACAnm2DAqyPfexjnbptQzzyyCM588wzc9ddd3WpHwAAAAB6ppovPLXLLrtkwIABWbRoUa1LAQAAAKCANmgG1qbykY98JCtXrqx1GQAAAAAUUCECrMmTJ9e6BAAAAAAKquanEAIAAABAewRYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACq0QVyHsqnK5XOsSuj2PYfew+nnyfHU/nrPic3x1X56z4nN8dV+es+JzfHVvnjfovFKlUqnUuggAAAAAWJ8eMQNr4cKFtS6hWxo6dGjK5XKam5uzePHiWpdDJ5TL5QwdOjSLFy9Oc3NzrcuhA46x7sXx1b04vroXx1f34vjqXhxf3U9Hx1hDQ0MNqoLi6xEBljfqrvMYdi/Nzc2es27G89V9OL66H89X9+H46n48X92H46t78pxB51nEHQAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAAAAABSaAAsAAACAQhNgAQAAAFBoAiwAAAAACk2ABQAAAEChCbAAAAAAKLRSpVKp1LoIauPiiy/OsmXLMmjQoLzzne+sdTnQ4zjGYNNxfMGm4/iCTcsxBhtHgNWLveUtb8mcOXMyZsyY/P73v691OdDjOMZg03F8wabj+IJNyzEGG8cphAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACi0PrUugNo58cQTs2zZsgwaNKjWpUCP5BiDTcfxBZuO4ws2LccYbJxSpVKp1LoIAAAAAFgfpxACAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNFch7IUWLVqUyy+/PHfccUfmz5+f/v37Z/vtt89b3vKWvO51r6t1edBtzZgxI3fccUcef/zxzJ49O4sXL87KlSszZMiQvOpVr8ob3/jG7L///qmr87cD6IoXX3wx1157be68887MmTMnTU1NaWhoyHbbbZfXvva1Oeigg2pdInQ7lUolt956a2644YY88cQTaWxszPDhwzNx4sQcddRR2X777WtdIhTW0qVL89BDD2XGjBl54oknMmPGjCxatChJ8qUvfSmTJk1qc7/m5ubcd999ueeeezJ9+vQ899xzWbFiRQYPHpxXvepVedOb3uR3R1iDqxD2Ms8880zOOuus1jfUgQMHZuXKlWlpaUmSHHnkkTn11FNrWSJ0WxdccEH+8Ic/tP5/wIABSZIVK1a03jZx4sR87nOfS319/WavD3qC22+/Pd/+9rezbNmyJEm/fv1SLpezfPnyJMmWW26ZH/7wh7UsEbqdVatW5Rvf+Eb+9re/JUnq6upSX1+fZcuWpVKppFwu54Mf/GAOOeSQGlcKxfTnP/85U6dObXNbewHWd7/73Vx//fWt/y+Xy+nfv38aGxtbb5s0aVI+97nPZeDAgdUtGrohM7B6kaamppx77rlZtGhRxo0bl49//OPZbrvtsnLlylxzzTX55S9/md/+9rfZbrvtcvDBB9e6XOh2dtppp2y11VbZZZddstVWW7WGVC+++GJuuOGG/PKXv8xDDz2Un/70pznttNNqXC10P/fdd1+++tWvZtWqVTnggANy3HHHZZtttkny8l+/H3vssTz66KM1rhK6n4suuih/+9vfUldXl5NPPjmHH354BgwYkBdffDEXX3xxrr/++lxwwQXZZptt8upXv7rW5UIhNTQ0ZPvtt8/48eMzduzYfOtb3+pwn1WrVqWhoSEHHXRQXv/61+dVr3pV6urqsnjx4vzmN7/J5ZdfngcffDDf/e5388lPfnIz3AsoNjOwepFrr702P/zhD9O/f/9ccMEFGT169Frbv//97+f3v/99RowYkR//+Mfp00e+CdV08cUX5//+7//Sr1+/XHbZZY4x2ADLly/Phz/84cybNy/HHntsTjnllFqXBD3CokWL8p73vCdNTU05+uij8573vGedNp/97Gfz0EMPZZdddslXvvKVGlQJxdbc3Jxyudz6/6VLl+bEE09M0v4MrMceeyzbbbdd+vXr1+b2Sy65JJdddlmS5Cc/+ck6n9+gt3EybS/yl7/8JUnyxje+sc03v+OOOy6lUikLFizIgw8+uJmrg55vhx12SJK89NJLWbJkSY2rge7lz3/+c+bNm5eRI0fmpJNOqnU50GPcf//9aWpqSpIcc8wxbbY5+uijkySPPPJInn/++c1VGnQba4ZXG2KnnXZab3iVZK01HWfMmLFRY0BPIsDqJZYvX57HH388SbLnnnu22Wb06NHZeuutk7z8ywxQXatPbRowYECGDx9e22Kgm1n9R5jXv/716du3b22LgR5k7ty5SZJBgwaloaGhzTarfz9MXj6VF9g8hg4d2vp9c3NzDSuBYnD+Si8xa9asrD5bdNy4cettN27cuDz77LN59tlnN1dp0KOtXLkyc+fOzY033pirrroqSXLEEUekVCrVuDLoPl566aU8+eSTSZLtt98+s2bNyq9+9avcf//9Wbp0aRoaGjJp0qQce+yxrWtiARtm9QV9Otr2zDPPbI5ygCQPPfRQ6/ftfYaD3kKA1UssWLCg9fsRI0ast93qbQsXLtzkNUFPtea6B2vq06dP3vrWt+ad73xnDaqC7mvOnDlZtWpVkmT27Nn53//936xcuTL9+vVLv379Mnfu3EybNi0333xzzjjjjEyePLnGFUP3MWbMmCQvz9afO3dum8tMrBlarfk7JbDpNDc359JLL03y8qmGr3zlK2tcEdSeUwh7iRUrVrR+379///W2W71t9eXIgQ1XV1eX4cOHZ/jw4a3rGpRKpbz1rW/Ncccdt9HrJEBvtXTp0tbvL7/88tTX1+fss8/O//3f/+Wyyy7Lt7/97YwfPz5NTU359re/ndmzZ9ewWuheJk2a1HpRkV//+tfrbK9UKrniiita/+93RNg8fvGLX2TGjBnp06dP3v/+99e6HCgEARZAldXX1+eiiy7KRRddlF//+tf50Y9+lCOPPDK//e1vc9ppp+WRRx6pdYnQrax5weSWlpZ87GMfy9577526upd/jXnVq16Vz33ucxkwYEBeeuml/OY3v6lVqdDtDB8+PIcffniS5A9/+EN+9rOfZe7cuVm1alWefvrpfPnLX87jjz/eGnI5BR42vRtuuCFXXnllkuTkk09uvRAQ9HZOIewlBgwY0Pr9ypUrU19f32a7lStXJkkGDhy4WeqCnq5UKmWLLbbI+973vowZMyY//vGP8/Wvfz3f//73250NCfw/a/5MeuUrX5k99thjnTYjRozIG9/4xlx//fUuRAIb6JRTTskLL7yQO+64I1dddVXrmo2rHXbYYZkxY0ZmzJiRQYMG1ahK6B1uvvnmfO9730vy8lXijzrqqBpXBMVhBlYvsea6V+2tXbB62/quQgNsvMMOOyx9+/bN/Pnzc/fdd9e6HOg21vwZtubV0P7V6m2rr6oGdE7fvn1z1lln5dOf/nRe97rXZezYsdliiy2y55575jOf+Uw+9KEPZdGiRUmSrbbaqsbVQs9122235Vvf+lZaWlpyxBFH5OSTT651SVAoZmD1EltvvXVKpVIqlUqeeeaZ9X4AWL1Ip0UCofr69euXIUOGZMGCBXnuuedqXQ50G0OHDk1DQ0OnLzDiFCfYcKVSKfvtt1/222+/dbYtXry4NRjeaaedNndp0Cvceeed+drXvpbm5uYcfPDB1r2CNpiB1UsMHDiw9dzpe+65p8028+bNy7PPPpsk2W233TZbbdBbLF++PIsXL07iNF3YULvvvnuSZNasWetts3rb6quqAdVx0003JXl5hv7qYxGonnvuuSdf+cpXsmrVquy///457bTT/DEG2iDA6kXe9KY3JXn5l5C2Tq+48sorU6lUMmLEiEyaNGkzVwfdW3Nz81oLTbflmmuuyapVq5IkEyZM2BxlQY9x4IEHJkmeffbZNv8Qs2DBgtYP2XvvvfdmrQ16sjlz5uSyyy5Lkhx77LGupAtV9sADD+S8885LU1NTXv/61+djH/tY60VKgLU5MnqRQw89NFtuuWVWrFiRL37xi3nqqaeSvLxw++WXX57f/e53SZJ3vvOdrVeaATpn3rx5OeOMM3L99devFRBXKpU8++yz+f73v59LL700SbLvvvtm3LhxtSoVuqXddtste+21V5Jk6tSpufvuu9PS0pIkeeqpp/KlL30pK1asyJAhQyx4CxvogQceyFVXXZXZs2enubk5ycuzhm+88cZ8+tOfzuLFizNp0qQceeSRNa4Uimvx4sWtX0uXLm29fdmyZWttW/3HzCSZPn16zj333Lz00kvZZ5998olPfEJIDO0oVTqaMkCP8swzz+Sss85qXYizvr4+K1asaP0Q8Na3vtX51rARXnjhhZx66qmt/+/Xr18GDBiQFStW5KWXXmq9/TWveU0++clPrnVlUKBzli5dms997nN58sknk7x8nPXp0yeNjY1JksGDB+ezn/1sJk6cWMsyodv585//nKlTpyZJ6urqUl9fn2XLlrXOLN57773zqU99ys8uaMfb3va2TrX70pe+1Hq2y1lnnZUHH3wwSTJkyJB2w6tjjjkmxxxzTNcLhW7MNJteZptttsl3vvOdXHHFFbnjjjsyb968DBo0KK961atyxBFH5HWve12tS4RuacSIEfnUpz6VBx54IP/4xz+ycOHCLF68OH379s1WW22VHXfcMfvvv3/23HPPWpcK3dbgwYPz9a9/Pb/73e9y00035Z///GdWrVqVrbbaKnvttVeOOeaYjBw5stZlQrez884756ijjsrDDz+cOXPmpLGxMQ0NDdlhhx1y4IEHZt999611idAjrTmXZMmSJe22Xb58+aYuBwrPDCwAAAAACs0aWAAAAAAUmgALAAAAgEITYAEAAABQaAIsAAAAAApNgAUAAABAoQmwAAAAACg0ARYAAAAAhSbAAgAAAKDQBFgAAAAAFJoACwAAAIBCE2ABAAAAUGgCLAAAAAAKTYAFAAAAQKEJsAAAAAAoNAEWAAAAAIUmwAIAAACg0ARYAJvIP//5z5xxxhmZOHFiBg8enFKplFKplG233XaD+pk5c2brvqeccsomqZXqKfLztWLFinzta1/Lvvvum4aGhpTL5dZaZ86cWevy2ACrn7c3velNtS5lo2277bYb9Z7IhvE4A9BT9Kl1AUD3M3PmzFx44YVJkje96U3d+gPUpvLYY49lv/32y/z582tdygbz/PZMy5cvz/77758777yzKv2tWrUqN910U6ZNm5bbb78906dPz7x581JXV5dRo0Zljz32yNve9rZMmTIl9fX1VRmzqK6++urcd999SZKPfexjGT58eE3rYeOdc845SV4OfToTQG9oewBg4wmwgA02c+bMfOELX2j9v4BjXZ/61Kdaw6vDDz88xx57bEaNGpUkhf8w7/ntmb7//e+3hle77LJLPvCBD2SrrbZKuVxOkowZM6bTfd1000057rjjMm/evDa3P/vss3n22Wfzm9/8Jv/93/+diy66KPvvv3/X70RBXX311fn5z3+eJDnllFMEWN3Y6ve+/fffv1OB1Ia2BwA2ngALoMqamppy/fXXJ0l22mmnXHvttamr2/gztrfddttUKpVqlUcv9bvf/S7Jy6ee/fGPf8zWW2+90X3Nnj27NbwaMmRIDj744Lzuda/LVlttlbq6ujz88MO56KKL8uyzz+aZZ57JYYcdluuvvz5veMMbqnJfAADofQRYAFU2b968rFixIkmy++67dym8gmp59tlnk7w806or4dVqO++8cz796U/n7W9/e5uzCj/72c/mXe96V6688sqsWLEi733vezN9+vTWGV8AALAhfKoCqLKVK1e2fj9gwIAaVgL/z+rXZTVek4cffngeeuihnHzyyes9Jba+vj4XX3xxxo4dmyR5/PHHc/PNN3d5bAAAeicBFmwGK1euzI9//OMce+yx2XbbbTNo0KD0798/r3zlK/OWt7wl3/jGNzJ79ux2+3j++efz3//935k8eXK23HLL9OvXL6NGjcrrX//6nHvuuVm4cGG7+7/pTW9qvWrValdddVWOOOKIbLXVVunfv3/Gjh2b4447LjfddFObffzlL39JqVTKAQcc0HrbF77whdZ+1/xa3xXNFi1alG9+85s5+OCDM3bs2PTv3z8jRozIXnvtlTPPPDP//Oc/270fp5xyyjpjXH311Tn22GMzbty49O/fv8tXVHv88cfz8Y9/PLvttlsaGhoyYMCAbL311jnyyCNz4YUXprm5uc39Vj/G2223XettP//5zzv92KxPZ65q1xuf33e84x2tbdd3n/7VkUce2brPXXfdtda2SqWSW2+9NWeffXbe/OY3Z+utt86AAQMycODAbL311nnb296Wn/70p3nppZc6NVY1vfjii/nKV76SN7zhDdliiy3Sr1+/jBkzJpMnT86Xv/zlvPjii23ud84557Te36effjpJ8vTTT6/zfK5etL+zhg0b1qmZhQMHDsyRRx7Z+v8HHnhgg8b5V/96NbUVK1Zk6tSp2XfffTN69OgMHDgw48ePz4c+9KE8/vjjHfY3b968/OxnP8vJJ5+c3XffPcOHD0/fvn0zYsSI7L777vnoRz+a6dOnr3f/1a/X1etfJcl22223zuPb3jpyDz74YP7zP/8ze+21V0aPHp2+fftm2LBh2WOPPfLBD34wf/jDH9LS0tLhfVmxYkXOP//87Lvvvhk5cmTrY/HBD34wTz31VIf7r/bEE0/kM5/5TF7zmtdk9OjR6devX7bYYosceOCBmTp1ahobGzvVz6xZs3LGGWdkp512Sn19fUaNGpXXvva1+eY3v5nly5d3up7Ouvfee3PeeefliCOOyHbbbZf6+vr0798/r3jFK3LIIYdk6tSpWbp06Xr3/9f3z7/+9a9tvvetPlY2tH3S9nv5iy++mPPOOy977rlnhg8fnkGDBmWXXXbJJz/5ycyZM6eqj1F7unosfO9732u9b1/60pc6NeaaP1++//3vr7fdfffdl49+9KPZbbfdMmLEiNafZ0cccUR++tOfZtWqVe2O86/H4YsvvpivfvWred3rXpcxY8akrq7OWo8A3UUF2KSmTZtW2WqrrSpJ2v3afffd19vH1KlTK/X19e3u39DQUPnDH/6w3j7233//1rbLly+vHH/88e3297WvfW2dPm688cYO78fqr6eeemqd/f/v//6vMmLEiHb3GzBgQOXCCy9c7/04+eSTW9s+9thjleOOO67T43fGF7/4xUqfPn3arXHChAmVGTNmtPsYb+hj056nnnqqdd+TTz65zTa98fm99tprW///3ve+t8PHcc6cOa3P7S677LLO9ne/+92duu+vfvWrK//4xz/WO05nnq8N8bvf/a7Dx3XEiBGV3/3ud+vs+/nPf75T9+lnP/tZl+tcn09+8pOt43zlK1/pUl/jxo2rJKmMGzeu8uyzz1Z22223jX6tPfHEEx0e60kqpVKp8t///d9t9rHm67W9r/3333+dfRsbGyvvfve7K6VSqcP9r7766nX2X7PvJ598sjJp0qT17j9o0KDKjTfe2O5j29zcXDnzzDM7fEy23nrryl133dVuX9dee21lyJAh6+1j4sSJlWeeeWat57MrvvCFL3TqeRg7dmzl9ttvb7OPzr73rT5WNrR9pbLue8Pdd99d2Wabbda77xZbbFF58MEHu/TYVCqVDh/nahwLixYtqgwaNKiSpLLttttWWlpa2q1p1apVla233rqSpDJ48ODK4sWL12mzYsWKynve854Oj5EJEyZUnnjiifWOteaxcs8997T5mLd1jAJQPNbAgk3o6quvztvf/vbWvw7uuOOOefvb356ddtop/fv3z3PPPZc77rgjv/vd79a7SPfnPve51r9mDho0KMcff3zrX9gXLFiQP//5z7niiiuycOHCvPWtb820adM6XCj5ve99by6//PJMnDgxU6ZMyfbbb59ly5blt7/9ba6++uokyac//ensu+++mTx5cut+EydOzFVXXZWHHnoo//Vf/5Ukecc73pETTjhhnTH+9YpmP/rRj/KBD3wglUol/fr1y1FHHZU3vvGN2WKLLbJ06dLccsstueSSS7JixYqccsop6devX6ZMmdLu/fjYxz6W6667LuPGjcu///u/59WvfnVWrFiRO+64I/37929337b813/9V84999wkL//F9rjjjsshhxySIUOG5LHHHsvPfvazPP3003n44Yez33775Z577mk9PSpJzj333MybNy9z5szJBz7wgSTJAQcckNNPP73dx6baesvze+ihh2aLLbbICy+8kMsvvzzf/e532z097tJLL209Ft/1rnets72xsTH9+vXL5MmT89rXvjbjx4/P0KFDs3LlysyYMSNXXnllHnjggTz66KM5/PDDc88992To0KHt3oeu+uMf/5ijjjqqte7Xvva1OeGEEzJ27Ng899xzueyyy3LbbbdlwYIFOeqoo3Lttdfm0EMPbd3/hBNOyO67754kef/735+5c+dm9OjR+eEPf7jWOHvuuecmuw8PPvhg6/fjxo2rSp9NTU15+9vfnvvvvz+77757TjrppGyzzTatr4WbbropK1asyHve854MHz48Rx111Dp9vPTSS1m1alW22WabHHTQQZk0aVLr7La5c+fmtttuy69//essX748Z599dkaOHJkPfehDa/Vx+umn5+ijj87555+fG2+8MUnygx/8YJ3jY/UVSFdbuXJl3vzmN+fWW29NkvTp0yfHHnts9t9//4wePTqNjY159NFHc8MNN+Tuu+9u9yIOixcvzhFHHJHp06fnkEMOyZFHHpktttgizz33XH7+85/nnnvuybJly3LCCSdk+vTpaWhoaLOfk08+ORdffHGSZMSIEXnHO96RvfbaK0OHDs2cOXPyu9/9Ltddd11mzZqVAw44IHfddVd23HHHdfq57bbbcuyxx7bOVNx7771z4oknZuzYsZk9e3YuueSS3HXXXXn729+epqam9d6vDdHY2JhyuZx99tkn++23X3bccccMHz48zc3NmTlzZq699trceuutmT17dg4//PDcd999eeUrX7lWH1dddVWS5JhjjkmSTJgwofXnwZpWHysb2v5fPfvss3nLW96SuXPn5rjjjsub3/zmjBgxIjNnzswPf/jDzJgxIy+88ELe8Y535L777kvfvn038tHpWDWOhaFDh+akk07KD3/4w8ycOTPXX3/9Wu9F/+r3v/99Zs2alSSZMmVKhgwZstb2VatW5bDDDstf/vKXJMnYsWNzwgknZNddd019fX1mzZqVK6+8MrfccksefvjhvPGNb8y9996b0aNHr3fM+fPn56ijjsqzzz6bN7/5za3HyvPPP79ZZ7sB0AW1zc+g55o5c+Zaf4H+whe+UFm1alWbbZcvX1659tpr17n9uuuua/3L4+te97rKrFmz2tz/lltuaR1r2223rTQ1Na3T5l9nB3384x+vNDc3r9Pui1/8YmubI488ss3x1pyp8/nPf76dR+Fl999/f6Vfv36VJJUddtihMn369DbbPfLII5WxY8dWklSGDBlSmT9//jpt/nXGw9FHH11Zvnx5hzV05LbbbqvU1dVV8v/P3LjuuuvWabN06dLKYYcd1jr24Ycf3mZf1Z6Bs6EzsHrT83vGGWe0tr3sssvarXPvvfeuJKnU1dVVnn322XW2//Wvf60sWLBgvfu3tLRUvvzlL7eO98UvfrHNdtV6/pcsWVLZYostWvs655xz1pnV0NLSUjn77LPXmrHR1kyGSqXjWRibwowZMyrlcrmSpNK3b9/KvHnzutTf6vuw+uu0005r8331q1/9amubMWPGVBYtWrROm/nz51duvvnmdsd76qmnKjvuuGMlSWXYsGGVJUuWtNluzddtZ2ZYfuQjH2ltv+OOO1YeffTR9bZ94IEHKo899tg6t6/5OPTp06fy61//ep02TU1Na71nffOb32xzjO9///trvS8sXLiwzXZXXHFF60yd/fbbb53tq1atquy8886tfZ1xxhnrvA81NzevddxW4zV5xx13VP75z3+22+YXv/hF63t8ezM2V9fU2Rk5G9J+zfeG1e+Df/3rX9dpt2TJksruu+/e2u6KK67oVC3r09GxX61j4d57722t+dhjj223v7e+9a2tbdua0feZz3ymdfupp5663p8DU6dObW130kkntdlmzce8XC5XLr744nZrA6C4BFiwifzHf/xH6y9MH/rQhzaqjz333LOSpDJ69Og2P+yv6Yc//GG7H+TXDDj233//9U7vX7VqVespjwMGDGgzDNvQgOOYY45p7e/xxx9vt+3111/f2ndbpxut+UFxq622Wu8Hyg117LHHtvbb1ul1q7344ouVLbfcsrXtfffdt06bWgdYven5XfMD01ve8pb1tps+fXpru4MOOqjD+9SeyZMnV5JUxo8f3+b2aj3/559/fqfuW6VSWSuk+Pa3v91mm80dYDU3N1cOOuig1rpOP/30Lve5ZoC19957txnSrrb6dZmkMnXq1I0e809/+lNrP+v74LshAdYzzzxT6du3b2uA0d6pT+1Z80P52Wefvd52a772Dz744HW2r1ixovKKV7yikqSy8847V1auXNnuuJ/97Gdb+7vtttvW2nbNNde0bttnn33W+z7U0tJS2WeffaoWYHXWO9/5zkqSSn19feWll15qs83mDLB++tOfrrftdddd19rufe97X6dqWZ9qHfudORb23Xff1lD1ueeea7PNM8880xps77XXXutsf+GFFyoDBgxY72v2X5144omt4VRbf+hb8zH/6Ec/2mF/ABSXRdxhE2hubs4ll1ySJOnfv3/OOeecDe7jwQcfzD333JMked/73pcRI0a02/7EE09Mnz4vnxX8xz/+sd22Z5xxxlqLz66pXC63LuK9YsWKPPHEExta+lpefPHFXHPNNUlePtVi/Pjx7bZ/85vfnFe84hVJOr4f73nPezJ48OAu1Ze8fDrP7373uyTJ4MGD1zk1Yk3Dhg1ba/uVV17Z5fGrrTc9v7vvvnt23XXXJMn111+/3tNALrrootbv//3f/73dPjuy+rTLGTNmZP78+V3qqz1rvrY+/elPt9v2s5/9bJv71dKZZ56ZP//5z0leXnz9C1/4QlX7/8QnPtHuQvKf+tSnWr+//PLLN3qcNU+zve222za6n9V+9atftZ46d+qpp+ZVr3pVl/qrq6vLRz/60fVuf/WrX52tt946SfLQQw+ts/3666/Pc889l+Tl03b79evX7ngnn3xy6/f/egyv+dpr732oVCrlP//zP9sdZ1NY/Vw2NjZ2+YICXTVq1Kg2T2Ve7YADDmj9md7W81YLnTkWPvjBDyZ5+RTAn/70p222+clPftJ6MZTVp9uv6Ve/+lVWrFiRJPnkJz/ZYV2rX5PNzc2t7znr86+n9APQvVgDCzaBBx54IIsXL06SvP71r293TYb1WfOqas3Nza1rF7Vn8ODBefHFF/PII4+0227fffdtd/vqDztJOry6YUduvfXW1ito9e/fv1P3Y8iQIXnuuec6vB8drfXVWffff39WrlyZJNlvv/0yaNCgdtsfeuihOfvss5NU5wNttfW25/ff//3f84lPfCKrVq3KJZdcko997GNrba9UKvnlL3+Z5OV15I477rj19rVq1apceeWVufrqq3Pfffdl9uzZWbJkyXqvAjdr1qyMHDmyU3VuiEqlkjvuuCNJUl9fv9YHx7asft0uW7Ysd955Z1paWjp1lcBN5Qc/+EG+9rWvJUkGDBiQX/3qVxk+fHhVxzj44IPb3f7a1742Q4YMyZIlS3L33Xev9zGZMWNGLrrootx000157LHHsmjRovVeJW/1mj1dcfPNN7d+39baXBtqp5126vAPHFtvvXVmzZrV5vG+5s+aJUuWdHgMr7lu1b8ew6tfs0ly0EEHtdtPR9s3VKVSyXXXXZfLL788d999d5599tksWbJkvVeomzVrVvbaa6+q1rAhXvOa17QGVG3p379/Ro0aleeff77L79OdVY1j4e1vf3vOOOOMzJ8/Pz/+8Y9z5plnrhVkNjc35yc/+UmSl38WtLUW4pqvyRdeeKHD1+SaV7dt7+fK2LFjuxwYA1BbAizYBNb8xW6XXXbZqD5mzpzZ+v3qD4KdtWDBgna3/+uCwv9qzQXQV/8VdGOteT8uvPDCtS4p3pGO7seaQUxXrJ59kKTNRYn/1Zpt1ty3KHrb83vSSSfl05/+dJqbm3PRRRetE2D99a9/zTPPPJMkOfbYY9cbUD722GM59thjOwzW1rQ6qK62xYsXp7GxMUmy/fbbdxhG1dXVZfz48bn//vuzfPnyvPjiix2GGpvKRRdd1DpLsV+/frnyyiuzzz77VHWMhoaGDoPDUqmU7bffPvfdd18aGxvbfEzOOeecfOlLX1pvyPGvqvF8V+Pnw5o6Ot6T/3fMrw7q17TmMfyJT3xig8b+12N49uzZSV5e0LujP9yMHDkyw4cPz4svvrhBY7bl+eefz/HHH9+6KH5nbKpjt7M25Hnr6vt0Z1TrWBgwYEDe85735Otf/3qeeuqp3HDDDTnkkENat6+5ePtJJ53U5izbNV+TGzpjtr2fK9X6nQGA2hFgwSaw5i92G3uKW1d+qV999af12ZwzM7pyPzq6QtXAgQM3uu81LVmypPX7jmZfJWs/p2vuWxS97fndcsstc8ghh+S6667Lvffem4cffjgTJkxo3b7m6YNrnv60pv+vvXsPirJ64wD+xWUXUBFRcnER8DKOl0IRFSslRkWRVhh0IC9cxHTUrHCkiZoc1DBNkyFMs/HSKhopXtHIC4WkpeIlFIxKojWzHEDFMBEz5P39sbPvbxH2grwLi30/M8ys63nPe97L2cuz5zynqqoKY8aMEb+Aq1QqqNVqDBgwAEqlEo6OjuJ53blzJzIzMwFAnAYjtabek0DD+7I1AlgZGRmYOXMm6urqoFAosHfvXoSEhEi+H0vPiWG5R8/J6tWrxWmN7dq1w+jRozFy5Eh4eXnB2dm53lQ6/UpzUlxvKd4fDDW3v0v5XnP37l0AulGDlujQoUOzA1j61eoKCwsB6IKboaGh8PHxgbu7O5ycnCCTyQAAx44dw9q1awFYr+9aqjVHSD5K6r4wd+5cpKSkQBAEbNy4sV4Aa8OGDfXKNcZan3+k+sxARESthwEsIivo1KmT+Fj/gb6pDL/YHDx4EKGhoc1uV2swPI6PPvoIr7/+eiu2pnGGy3dXV1ebLW94TR9d+vu/xlaub2xsLA4fPgxAF7BatWoVAKCmpgZ79+4FAHh6eor5vx61bt06MXgVFRUFjUZjNBdQU0Z5PK6m3pNA69+XGRkZmDFjBurq6iCXy7F7925MnDjRKvuy9JwYljM8J/fv30dycjIA3T2cm5trdJSYpfuy1KPvD46OjpLW31SGfbioqAg+Pj7NqquqqkocPWiOFOc2MzNTDF6NHTsW+/fvN3r/G041Ix1r9IU+ffpg/PjxOHr0KA4ePIjy8nIolUpcu3YNR44cAQD4+/vD19e30e0N78k7d+78599niYjo/2zn5x+iJ4jhMPWmTEcyVse1a9ea3abW0haOQ59UHAB++eUXs+VLSkrExyqVyiptaits5fqGh4eLgYGMjAwxZ1VWVpY44iUqKsroqIecnBwAgL29PdauXWsykfWVK1ekbHqjOnXqJI4e0mq1RnNw6dXV1YkJ+Z2cnCTPN2WOPnj18OFDyOVy7Nq1C2FhYVbb3+3bt81OQRUEAVqtFoBuRJDhOTl9+rQY8Js7d67JKY5SX28p3h+kJGUf9vDwAKALOty4ccNk2Vu3bkkyfVDfdwEgLS3NZLCjJfpuW2OtvqCfRvzvv/+Kydw3b95sMnm7nq28rxARke1hAIvICgYNGgQXFxcAwKlTp8x+kG9MYGCg+Fg/ssRWGAYBBEEwWTYgIEBM4Kr/5dXW+Pr6irlGvvvuO7OjBwxX3hoxYoRV29Ya2uL1dXR0xEsvvQRAN8ri2LFjAIDt27eLZUzlUikrKwOgy8vj6upqtNz9+/fxzTffSNBi0+zs7DB8+HAAulEP5kZ9nTx5UvwSOnz48BadnmQYvLK3t8fOnTsRHh5u9f1+9dVXJv//7NmzYvBy2LBh9c6J/noDMLtypiWvv03pMy+88IL4WL+CZ2uS8r3GMPih74PGmFstzlJNuZaWvEbpX8/MXcfHLW9rpO4Lemq1Gp6engB0gSvDQJaLiwumTp1qdFtb/vxDREStiwEsIiuQyWSIiooCoEuau3Tp0ibXMXToUDzzzDMAgC+//LJFpi1ZynB4v7kpBd26dRNz4Fy6dAk7duywatseh0KhEKc63b17F+vXrzda9s6dO/jkk0/Ef5ta0a6taqvX1zBAtW3bNpSXl4ujM4YNG4YBAwYY3VY/2qmiosJkcuc1a9bg1q1bErXYNMN7Sz8l0piVK1c2up217dixo0HwavLkyS2y79TUVJNBg5SUFPFxREREvf8zzI1VWlpqtI7bt28jLS3NbFua0memTJkijvDbuHGjOEqstYSEhIgJ1zUajcnzYY4+PxKgGw1l7PoIgoAPP/zwsfdjyNJrmZmZieLiYrP16a+lpdPlmlre1kjdF/RkMhnmzJkDQDeKNCEhQUzeHh0dbTJP2tSpU8UflVJTU3Hz5k2L90tERE82BrCIrOStt94SpzStX78eycnJRpOe/vPPPw1+ZbSzsxO/lAqCgPDwcHz99dcm93n9+nUsXboURUVFEhyBcb169RIfFxQUmC2/fPly8Qvb7NmzzQY5KisrkZqaavZ4pfTmm2+KoyiSkpLqjbLSu3fvHqZPny6uPPjiiy9i0KBBLdbGltJWr++oUaPEtu/btw+bNm0S+5y5laz0o50EQcCiRYsaLbNjxw4kJSVJ2GLT4uLioFQqAeiC2MuWLWu03LJly3Do0CEAgFKpxMyZM1ukfZmZmYiJiakXvGrJ4NnZs2excOHCRqdXpqamYs+ePQB0QdZHk/cPGzZMHDmzefNmcfqlocrKSoSHh4u50UxpSp/p0aMHXnnlFQC6gHlISAguX75stHxxcbFFU5sfV4cOHcQfWe7du4fg4GBcuHDB5DalpaVISEhARUVFvef1Cx8AQH5+PhITExsEsQRBQGJiIvLz8yVpv77vAsCiRYsafZ/Ny8sTgynm6K/lzz//jJqaGsnL2xqp+4Kh2bNnQy6XA9DlGdQzNX0Q0PWR+Ph4ALrPNcHBwWYDvYWFhWbrJSKito9J3ImsxMvLC+np6YiMjERtbS2WLFmCjIwMREZGon///lAoFCgvL8f58+eRnZ0NT0/PBqt1qdVqJCcnY/Hixbh58ybGjRuHgIAATJgwAT179oRcLsdff/2Fy5cv49SpU8jPz4cgCAgKCrLqsbm6usLPzw8FBQXIy8vD3LlzERQUVC/3SGBgoLjij6+vLzZs2IBZs2aJQaAPPvgAoaGh6Nu3L5ycnFBVVYXS0lKcPXsWJ06cQG1tbb3pX9Y2YsQIvPPOO3jvvfdw//59hISEICIiAuPHj4ezszNKSkqg0WjE5b2VSiU2bdrUYu1rSW31+trZ2SE2NhbvvvsuqqurxYCPXC7HtGnTTG772muvQaPRoLa2FuvWrUNBQQEiIiLg4eGB8vJyHDhwALm5uejYsSPCwsLExPDW1LFjR6Snp0OtVuPhw4dYvHgxDh8+jClTpqB79+4oKyvDzp07cfr0aQC6/F3p6ektkvD4yJEjiI6OFoMF06ZNg0wmQ1ZWlsntvLy84Ofn1+z9q1QqeHl5Yc2aNThx4gSioqLg6emJiooK7NmzB8ePHweguyc2btxYL3G6fvvIyEjs2rULVVVV8PX1xezZszF48GDY29vjwoULSE9Px61btxAXF4etW7eabI/ha25iYiIqKirQr18/8ct7ly5d6k2vW7VqFc6dO4dTp06hpKQEPj4+mDRpEgIDA9GtWzfcu3cPJSUlyM3NxZkzZ7Bv3z707du32efNmPnz5+P777+HRqOBVqvF0KFDERwcjLFjx6JHjx6ws7NDZWUlfvrpJ3z77be4ePEiACAhIaFePTKZDBqNBoGBgXjw4AFSUlJw/PhxTJ8+HSqVCtevX8fnn3+Oc+fOYcSIEbh27VqTgyKPmjVrFt5//338/fffOHjwIAYPHozY2Fh4e3vj9u3bOHr0KA4cOIB27dohOjoan332mcn6goKCUFRUhOrqaoSGhiI2NhZPPfWUGOTx8fERc309TnlbI3VfMOTu7o5JkyZh165d4nPPPfecRQsFrFixAoWFhcjJyUFBQQH69++PsLAwBAQEoHv37qirq8PNmzfxww8/IC8vDyUlJZDJZPVWOSQioieQQERWlZOTI7i7uwsATP4NGTLEaB3p6emCq6ur2ToACM7OzkJRUVGDOgIDA8Uy5ixZskQsm5eX12iZI0eOCPb29kbbceXKlUa3UalUFh2Hg4ODcPjw4QZ1zJgxw+Q+mis5OdnkcQEQBg4cKJSWlhqt48qVK2LZGTNmNLtNltTH66vz66+/NthXWFiYRdt++umnJo+5a9euwtGjR82eP6mvf3Z2ttn+7+rqKmRnZ5usx9vbWwAgeHt7N7tNhuegKX/NPR+Gx/DHH38IgwcPNnmPbdmyxWhdlZWVgp+fn8n2RkRECDU1NeK/AwMDjdYXHR1ttJ7Gtquurja5jeHfgQMHGmxvSZv0LHl9qKurE1atWiW0b9/eoja5ubkJN27caLSuL774QnB2dja6rY+Pj/D7779Ldk8eOnTIZLvbt28vbNu2TdiyZYv4nLF7488//xSUSqXRuh7drinlm/raINX5MVeP1H3BUF5eXr16tm7danG7Hzx4ILzxxhtm35P1f8aOr6ltJiIi28UphERWNm7cOGi1Wnz88ceYMGECVCoVFAoFHBwc4OXlBbVajbS0tEanrOnFxsbi6tWrWLt2LSZOnAhPT084OTlBLpfDzc0N/v7+mDdvHnbv3o2ysrJmLYNuqeDgYJw+fRoxMTHo06ePyXwWhttotVpoNBpERESgV69e6NixI+zt7eHq6oohQ4YgLi4O27ZtQ1lZGSZMmGD143hUUlISiouLsXDhQvj4+MDFxQUKhQIqlQpqtRpbtmxBYWEh+vTp0+Jta0lt9fr27t0bo0aNqvecuemDei+//DLOnDmDqKgo9OjRA3K5HF26dIGvry+SkpJQVFSE8ePHS95mc9RqNbRaLVasWIGRI0fCzc0N9vb2cHNzw/PPP4/ly5dDq9VCrVa3eNtak4eHB/Lz85GWloZnn30WXbt2hYODA3r37o158+bh0qVLiIuLM7q9q6srTp48idTUVPj7+8PZ2Vl8XZ48eTL279+P3bt3w9HR0aL2pKenY9OmTRgzZgy6desmjr4ypn379ti+fTvOnz+PV199FU8//TRcXFwgk8nQuXNn+Pn5Yf78+cjNzUVoaGhTTs1jsbOzQ2JiIn777TesXLkSQUFBUKlUcHBwgIODA5RKJUaOHIkFCxYgOzsb169fh5ubW6N1TZw4ET/++CMWLFiAvn37wtHREV26dMHw4cORkpKC/Px8McG3FEJCQlBYWIg5c+agV69eUCgUcHFxwcCBA5GQkICLFy8iJibGorpUKhUKCgqQkJCAQYMGwdnZWRxNJUV5WyR1XzA0atQocbRu586dxcU2LCGXy5GSkoLS0lIsXrwYAQEBcHd3h0KhgKOjIzw8PDB69Gi8/fbbyMvLa/V8ckREZH12gtBGl00hIiKi/5SePXvi6tWr8Pb2FqfzEpHtysrKEpP7x8fHY82aNa3cIiIiass4AouIiIiIiCRnuGrvvHnzWrElRET0JGAAi4iIiIiIJHXixAnk5OQA0E0x169QSURE9Li4CiERERERETVLTU0Njh8/jtraWhQXF2P16tUAdPnVkpOTW7l1RET0JGAAi4iIiIiImqW8vBwhISENnk9MTIS/v38rtIiIiJ40DGAREREREZFkOnXqhH79+iE+Ph5RUVGt3RwiInpCcBVCIiIiIiIiIiKyaUziTkRERERERERENo0BLCIiIiIiIiIismkMYBERERERERERkU1jAIuIiIiIiIiIiGwaA1hERERERERERGTTGMAiIiIiIiIiIiKbxgAWERERERERERHZNAawiIiIiIiIiIjIpjGARURERERERERENo0BLCIiIiIiIiIismkMYBERERERERERkU37H/W3jPtHGdsWAAAAAElFTkSuQmCC"
-          },
-          "metadata": {
-            "image/png": {
-              "height": 900,
-              "width": 600
-            }
-          },
-          "output_type": "display_data"
-        },
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "\n"
-          ]
-        }
-      ],
-      "source": [
-        "\n",
-        "for stream in [\"block_output\", \"mlp_activation\", \"attention_output\"]:\n",
-        "    df = pd.read_csv(f\"./tutorial_data/pyvene_rome_{stream}.csv\")\n",
-        "    df[\"layer\"] = df[\"layer\"].astype(int)\n",
-        "    df[\"pos\"] = df[\"pos\"].astype(int)\n",
-        "    df[\"p(hate)\"] = df[\"prob\"].astype(float)\n",
-        "    #custom_labels = [\"imagine*\",\"the*\", \"riots*\", \"if\", \"people\", \"actually\", \"got\" ,\"food\" ,\"boxes\" ,\"instead\", \"of\" ,\"ebt\", \"cards\", \"every\", \"ghetto\", \"in\", \"america\", \"would\" ,\"look\", \"like\", \"ferguson\"]\n",
-        "    custom_labels = base_token #[\"what*\", \"sort*\", \"of*\", \"white*\",\"man\" ,\"or\", \"woman\", \"would\", \"vote\", \"for\", \"this\", \"nigger\"]\n",
-        "    #custom_labels = [\"no*\", \"liberal*\",\"congratulated*\", \"hindu*\", \"refugees\", \"post\", \"cab\", \"because\", \"they\", \"hate\", \"hindus\"]\n",
-        "    breaks = list(range(len(custom_labels)))#[0, 1, 2, 3, 4, 5, 6,7,8,9,10,11]\n",
-        "\n",
-        "\n",
-        "    plot = (\n",
-        "        ggplot(df, aes(x=\"layer\", y=\"pos\"))    \n",
-        "\n",
-        "        + geom_tile(aes(fill=\"p(hate)\"))\n",
-        "        + scale_fill_cmap(colors[stream]) + xlab(titles[stream])\n",
-        "        + scale_y_reverse(\n",
-        "            limits = (-0.5, 12), \n",
-        "            breaks=breaks, labels=custom_labels) \n",
-        "        + theme(figure_size=(6,9)) + ylab(\"\") \n",
-        "        + theme(axis_text_y  = element_text(angle = 90, hjust = 1))\n",
-        "    )\n",
-        "    ggsave(\n",
-        "        plot, filename=f\"./tutorial_data/pyvene_rome_{stream}.pdf\", dpi=200\n",
-        "    )\n",
-        "    print(plot)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    }
-  ],
-  "metadata": {
-    "accelerator": "GPU",
-    "colab": {
-      "gpuType": "T4",
-      "provenance": []
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.10.12"
-    },
-    "widgets": {
-      "application/vnd.jupyter.widget-state+json": {
-        "02750c86a66b4524942b36ca673e8441": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HBoxModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HBoxModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "HBoxView",
-            "box_style": "",
-            "children": [
-              "IPY_MODEL_8efe2ff3e4d04af59a71f25da5c07f78",
-              "IPY_MODEL_2a73966ed0dc48d78befbd340764cab7",
-              "IPY_MODEL_a133914642d3445bb68ebddbd8fb4af0"
-            ],
-            "layout": "IPY_MODEL_12c7dcf05527489b8e5473fbccfb1afe",
-            "tabbable": null,
-            "tooltip": null
-          }
-        },
-        "071c7cf6402f4a6181d4b469bde1b3cb": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "VBoxModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "VBoxModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "VBoxView",
-            "box_style": "",
-            "children": [
-              "IPY_MODEL_85c8c1e35cef4d748533c9dddb02896e",
-              "IPY_MODEL_1e5cefa47c0f4818865b5d09ca710cc0",
-              "IPY_MODEL_45be68901a2a4d8fbec05de19c92c324",
-              "IPY_MODEL_849d1b8eef1244e68915e92fcd2b21ce",
-              "IPY_MODEL_6da6c2eb83ea4ba0acd528286ce446c8"
-            ],
-            "layout": "IPY_MODEL_34f422b8c7b34f2d9363f35dd5d6d0ff",
-            "tabbable": null,
-            "tooltip": null
-          }
-        },
-        "08c5c590a2b34d72a7a55bfe6fe9dafa": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "0c48b20e1c474468b313c5084963889e": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "HTMLView",
-            "description": "",
-            "description_allow_html": false,
-            "layout": "IPY_MODEL_5f0246adc4e74fde960262d56a27c3d0",
-            "placeholder": "​",
-            "style": "IPY_MODEL_55b5c659d4ff4784a9bbf3173399b3e0",
-            "tabbable": null,
-            "tooltip": null,
-            "value": " 2/2 [01:00&lt;00:00, 27.61s/it]"
-          }
-        },
-        "12c7dcf05527489b8e5473fbccfb1afe": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "17c0de2c2bf74b2ea14c1e6306accf87": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "CheckboxStyleModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "CheckboxStyleModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "StyleView",
-            "background": null,
-            "description_width": ""
-          }
-        },
-        "1c7ded73ed064fe88b072fc1ce59bf5a": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "1e5cefa47c0f4818865b5d09ca710cc0": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "PasswordModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "PasswordModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "PasswordView",
-            "continuous_update": true,
-            "description": "Token:",
-            "description_allow_html": false,
-            "disabled": false,
-            "layout": "IPY_MODEL_08c5c590a2b34d72a7a55bfe6fe9dafa",
-            "placeholder": "​",
-            "style": "IPY_MODEL_31516d3aeee84dd88edd9a1959d1def7",
-            "tabbable": null,
-            "tooltip": null,
-            "value": ""
-          }
-        },
-        "2a73966ed0dc48d78befbd340764cab7": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "FloatProgressModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "FloatProgressModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "ProgressView",
-            "bar_style": "",
-            "description": "",
-            "description_allow_html": false,
-            "layout": "IPY_MODEL_ba1dd1977a88451cae4242c57aeed255",
-            "max": 2,
-            "min": 0,
-            "orientation": "horizontal",
-            "style": "IPY_MODEL_702c06dda74447a3a36142f7f6dd50d7",
-            "tabbable": null,
-            "tooltip": null,
-            "value": 1
-          }
-        },
-        "31516d3aeee84dd88edd9a1959d1def7": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "TextStyleModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "TextStyleModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "StyleView",
-            "background": null,
-            "description_width": "",
-            "font_size": null,
-            "text_color": null
-          }
-        },
-        "34f422b8c7b34f2d9363f35dd5d6d0ff": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": "center",
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": "flex",
-            "flex": null,
-            "flex_flow": "column",
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": "50%"
-          }
-        },
-        "38773bbb85ac406da4ccf19ae1a0a586": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLStyleModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLStyleModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "StyleView",
-            "background": null,
-            "description_width": "",
-            "font_size": null,
-            "text_color": null
-          }
-        },
-        "3e18465f9ad1485fa27b63d2b3f98914": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HBoxModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HBoxModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "HBoxView",
-            "box_style": "",
-            "children": [
-              "IPY_MODEL_625691ae152e40879829d255ad5c60bc",
-              "IPY_MODEL_7f5572f404bf469b90b06f6f89ea5af4",
-              "IPY_MODEL_0c48b20e1c474468b313c5084963889e"
-            ],
-            "layout": "IPY_MODEL_a875503fde864b18902ec6efa72a756c",
-            "tabbable": null,
-            "tooltip": null
-          }
-        },
-        "45be68901a2a4d8fbec05de19c92c324": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "CheckboxModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "CheckboxModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "CheckboxView",
-            "description": "Add token as git credential?",
-            "description_allow_html": false,
-            "disabled": false,
-            "indent": true,
-            "layout": "IPY_MODEL_ac1a886161c84d21b47627f5796906a9",
-            "style": "IPY_MODEL_17c0de2c2bf74b2ea14c1e6306accf87",
-            "tabbable": null,
-            "tooltip": null,
-            "value": true
-          }
-        },
-        "55b5c659d4ff4784a9bbf3173399b3e0": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLStyleModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLStyleModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "StyleView",
-            "background": null,
-            "description_width": "",
-            "font_size": null,
-            "text_color": null
-          }
-        },
-        "5f0246adc4e74fde960262d56a27c3d0": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "60e7eaa94497433190fc974f18eceb7a": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "625691ae152e40879829d255ad5c60bc": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "HTMLView",
-            "description": "",
-            "description_allow_html": false,
-            "layout": "IPY_MODEL_cc901f6a4aab456aa49f71850967d233",
-            "placeholder": "​",
-            "style": "IPY_MODEL_668effd825244964b1f46a23a387ff6d",
-            "tabbable": null,
-            "tooltip": null,
-            "value": "Loading checkpoint shards: 100%"
-          }
-        },
-        "668effd825244964b1f46a23a387ff6d": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLStyleModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLStyleModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "StyleView",
-            "background": null,
-            "description_width": "",
-            "font_size": null,
-            "text_color": null
-          }
-        },
-        "6da6c2eb83ea4ba0acd528286ce446c8": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "HTMLView",
-            "description": "",
-            "description_allow_html": false,
-            "layout": "IPY_MODEL_d124971d76e645adb551aa5244485b96",
-            "placeholder": "​",
-            "style": "IPY_MODEL_38773bbb85ac406da4ccf19ae1a0a586",
-            "tabbable": null,
-            "tooltip": null,
-            "value": "\n<b>Pro Tip:</b> If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. </center>"
-          }
-        },
-        "702c06dda74447a3a36142f7f6dd50d7": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "ProgressStyleModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "ProgressStyleModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "StyleView",
-            "bar_color": null,
-            "description_width": ""
-          }
-        },
-        "7f5572f404bf469b90b06f6f89ea5af4": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "FloatProgressModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "FloatProgressModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "ProgressView",
-            "bar_style": "success",
-            "description": "",
-            "description_allow_html": false,
-            "layout": "IPY_MODEL_8eba3af3e6274b5497c85dcaf9d4f767",
-            "max": 2,
-            "min": 0,
-            "orientation": "horizontal",
-            "style": "IPY_MODEL_ec3809f996b743cc8c5af1d06ca8a6ad",
-            "tabbable": null,
-            "tooltip": null,
-            "value": 2
-          }
-        },
-        "8454b87258ab47f2afdc3e8d48e82e32": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLStyleModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLStyleModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "StyleView",
-            "background": null,
-            "description_width": "",
-            "font_size": null,
-            "text_color": null
-          }
-        },
-        "849d1b8eef1244e68915e92fcd2b21ce": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "ButtonModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "ButtonModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "ButtonView",
-            "button_style": "",
-            "description": "Login",
-            "disabled": false,
-            "icon": "",
-            "layout": "IPY_MODEL_1c7ded73ed064fe88b072fc1ce59bf5a",
-            "style": "IPY_MODEL_c357088019794100828bce478d88bb36",
-            "tabbable": null,
-            "tooltip": null
-          }
-        },
-        "85c8c1e35cef4d748533c9dddb02896e": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "HTMLView",
-            "description": "",
-            "description_allow_html": false,
-            "layout": "IPY_MODEL_60e7eaa94497433190fc974f18eceb7a",
-            "placeholder": "​",
-            "style": "IPY_MODEL_8454b87258ab47f2afdc3e8d48e82e32",
-            "tabbable": null,
-            "tooltip": null,
-            "value": "<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svg\nalt='Hugging Face'> <br> Copy a token from <a\nhref=\"https://huggingface.co/settings/tokens\" target=\"_blank\">your Hugging Face\ntokens page</a> and paste it below. <br> Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. </center>"
-          }
-        },
-        "8eba3af3e6274b5497c85dcaf9d4f767": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "8efe2ff3e4d04af59a71f25da5c07f78": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "HTMLView",
-            "description": "",
-            "description_allow_html": false,
-            "layout": "IPY_MODEL_9f00991060be45bf8b2020a438501d1d",
-            "placeholder": "​",
-            "style": "IPY_MODEL_efe880306f44444aa51eb239e7d59b13",
-            "tabbable": null,
-            "tooltip": null,
-            "value": "Loading checkpoint shards:  50%"
-          }
-        },
-        "9f00991060be45bf8b2020a438501d1d": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "a133914642d3445bb68ebddbd8fb4af0": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLModel",
-          "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "2.0.0",
-            "_view_name": "HTMLView",
-            "description": "",
-            "description_allow_html": false,
-            "layout": "IPY_MODEL_e0b89135d45d4a09a6a7ba00311e9fd7",
-            "placeholder": "​",
-            "style": "IPY_MODEL_d48c867b20b7425f8885ea513d18c9ea",
-            "tabbable": null,
-            "tooltip": null,
-            "value": " 1/2 [00:46&lt;00:46, 46.70s/it]"
-          }
-        },
-        "a875503fde864b18902ec6efa72a756c": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "ac1a886161c84d21b47627f5796906a9": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "ba1dd1977a88451cae4242c57aeed255": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "c357088019794100828bce478d88bb36": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "ButtonStyleModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "ButtonStyleModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "StyleView",
-            "button_color": null,
-            "font_family": null,
-            "font_size": null,
-            "font_style": null,
-            "font_variant": null,
-            "font_weight": null,
-            "text_color": null,
-            "text_decoration": null
-          }
-        },
-        "cc901f6a4aab456aa49f71850967d233": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "d124971d76e645adb551aa5244485b96": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "d48c867b20b7425f8885ea513d18c9ea": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLStyleModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLStyleModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "StyleView",
-            "background": null,
-            "description_width": "",
-            "font_size": null,
-            "text_color": null
-          }
-        },
-        "e0b89135d45d4a09a6a7ba00311e9fd7": {
-          "model_module": "@jupyter-widgets/base",
-          "model_module_version": "2.0.0",
-          "model_name": "LayoutModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/base",
-            "_model_module_version": "2.0.0",
-            "_model_name": "LayoutModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "LayoutView",
-            "align_content": null,
-            "align_items": null,
-            "align_self": null,
-            "border_bottom": null,
-            "border_left": null,
-            "border_right": null,
-            "border_top": null,
-            "bottom": null,
-            "display": null,
-            "flex": null,
-            "flex_flow": null,
-            "grid_area": null,
-            "grid_auto_columns": null,
-            "grid_auto_flow": null,
-            "grid_auto_rows": null,
-            "grid_column": null,
-            "grid_gap": null,
-            "grid_row": null,
-            "grid_template_areas": null,
-            "grid_template_columns": null,
-            "grid_template_rows": null,
-            "height": null,
-            "justify_content": null,
-            "justify_items": null,
-            "left": null,
-            "margin": null,
-            "max_height": null,
-            "max_width": null,
-            "min_height": null,
-            "min_width": null,
-            "object_fit": null,
-            "object_position": null,
-            "order": null,
-            "overflow": null,
-            "padding": null,
-            "right": null,
-            "top": null,
-            "visibility": null,
-            "width": null
-          }
-        },
-        "ec3809f996b743cc8c5af1d06ca8a6ad": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "ProgressStyleModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "ProgressStyleModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "StyleView",
-            "bar_color": null,
-            "description_width": ""
-          }
-        },
-        "efe880306f44444aa51eb239e7d59b13": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "2.0.0",
-          "model_name": "HTMLStyleModel",
-          "state": {
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "2.0.0",
-            "_model_name": "HTMLStyleModel",
-            "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "2.0.0",
-            "_view_name": "StyleView",
-            "background": null,
-            "description_width": "",
-            "font_size": null,
-            "text_color": null
-          }
-        }
-      }
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}