Update v2

README.md

@@ -7,18 +7,16 @@ library_name: transformers
 tags:
 - llama
 - LLM
-datasets:
-- tatsu-lab/alpaca
 inference: false
 ---
 
 <p align="center" width="100%">
-<img src="https://huggingface.co/bofenghuang/vigogne-chat-7b/resolve/main/vigogne_logo.png" alt="Vigogne" style="width: 40%; min-width: 300px; display: block; margin: auto;">
+<img src="https://huggingface.co/bofenghuang/vigogne-7b-chat/resolve/main/vigogne_logo.png" alt="Vigogne" style="width: 40%; min-width: 300px; display: block; margin: auto;">
 </p>
 
-# Vigogne-Chat-7B: A French Chat LLaMA Model
+# Vigogne-7B-Chat: A French Chat LLaMA Model
 
-Vigogne-Chat-7B is a LLaMA-7B model fine-tuned to conduct multi-turn dialogues in 🇫🇷 French between human user and AI assistant.
+Vigogne-7B-Chat is a LLaMA-7B model fine-tuned to conduct multi-turn dialogues in 🇫🇷 French between human user and AI assistant.
 
 For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
 
@@ -26,28 +24,38 @@ For more information, please visit the Github repo: https://github.com/bofenghua
 
 ## Usage
 
-This repo only contains the low-rank adapter. In order to access the complete model, you also need to load the base LLM model and tokenizer.
-
 ```python
-from peft import PeftModel
-from transformers import LlamaForCausalLM, LlamaTokenizer
-
-base_model_name_or_path = "name/or/path/to/hf/llama/7b/model"
-lora_model_name_or_path = "bofenghuang/vigogne-chat-7b"
-
-tokenizer = LlamaTokenizer.from_pretrained(base_model_name_or_path, padding_side="right", use_fast=False))
-model = LlamaForCausalLM.from_pretrained(
-    base_model_name_or_path,
-    load_in_8bit=True,
-    torch_dtype=torch.float16,
-    device_map="auto",
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
+from vigogne.preprocess import generate_inference_chat_prompt
+
+model_name_or_path = "bofenghuang/vigogne-7b-chat"
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side="right", use_fast=False)
+model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, device_map="auto")
+
+user_query = "Expliquez la différence entre DoS et phishing."
+prompt = generate_inference_chat_prompt([[user_query, ""]], tokenizer=tokenizer)
+input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to(model.device)
+input_length = input_ids.shape[1]
+
+generated_outputs = model.generate(
+    input_ids=input_ids,
+    generation_config=GenerationConfig(
+        temperature=0.1,
+        do_sample=True,
+        repetition_penalty=1.0,
+        max_new_tokens=512,
+    ),
+    return_dict_in_generate=True,
 )
-model = PeftModel.from_pretrained(model, lora_model_name_or_path)
+generated_tokens = generated_outputs.sequences[0, input_length:]
+generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
+print(generated_text)
 ```
 
-<!-- You can infer this model by using the following Google Colab Notebook.
+You can infer this model by using the following Google Colab Notebook.
 
-<a href="https://colab.research.google.com/github/bofenghuang/vigogne/blob/main/notebooks/infer_instruct.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a> -->
+<a href="https://colab.research.google.com/github/bofenghuang/vigogne/blob/main/notebooks/infer_chat.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
 
 ## Limitations
 

adapter_config.json

@@ -1,22 +0,0 @@
-{
-  "base_model_name_or_path": "huggyllama/llama-7b",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "target_modules": [
-    "q_proj",
-    "v_proj",
-    "k_proj",
-    "o_proj",
-    "gate_proj",
-    "down_proj",
-    "up_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "huggyllama/llama-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

adapter_model.bin → pytorch_model-00001-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a8c8bf51e0cd3fbacd1391c60445844ac65f20b6ac3617d99ea13de542a737
-size 40047549
+oid sha256:c151b5a19d0e4b9be25e7d5230d089ed3b73f168343f2e561e455013bee0e127
+size 1981889895

runs/1/1683884762.493527/events.out.tfevents.1683884762.koios.zaion.ai.224530.1 → pytorch_model-00002-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37130027386eb12a9a683dcf5e52df1bbd2d948e93eafa9f2c3381e339134034
-size 6010
+oid sha256:b51597e102e5487fae308ce8fcfb004965ca07f74b0d5f75311b22684941ac9c
+size 1990296833

runs/1/1683888216.0705674/events.out.tfevents.1683888216.koios.zaion.ai.234743.1 → pytorch_model-00003-of-00007.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5daf3014f1d749ef42e5bd7d69ffed5279f81b7d77b2e89ba9615f679990826
-size 6010
+oid sha256:22fa0ba002b16f0675075cc64be3fd332e10b5229a1bb70152c4d6783636f7fd
+size 1990296833

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e60bbcee722698393786e9f3f30214d871116bc473e41a4dc5ad0d75c79e15
+size 1990296897

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59cc3e64641c1e07402e6e6f79323f6a2f9b0da3cb4dcfe7aa219643e1ae76e5
+size 1933656733

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d50f7469f5bf68c53cc4c717a30ca03137c98e13e27f8e601ec1580bcc09e4e
+size 1933673793

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efbab49da9bf358c394798ac6b4f0fc9b93f3cf1a0e17f07904a8b653d274f98
+size 1656836567

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 13476839424
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00007-of-00007.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.norm.weight": "pytorch_model-00007-of-00007.bin"
+  }
+}

runs/1/events.out.tfevents.1683884762.koios.zaion.ai.224530.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5874cd25670604e5413619d1be4be6f21a45dd191d8fabbd830dd67ae236231c
-size 4056

runs/1/events.out.tfevents.1683888216.koios.zaion.ai.234743.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:65c312df17a5edf956db8dd8511b48e564d65335f42cac0f0be667565c317637
-size 5442

runs/1/events.out.tfevents.1683893771.koios.zaion.ai.249409.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ce50e905326e06cf4cbbdcd0039fe63b6888ac38f523b2a839baa139b19f10de
-size 53017

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

runs/1/1683893771.5868623/events.out.tfevents.1683893771.koios.zaion.ai.249409.1 → tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ede703f88b2c0280493972a833791e0a5eae1742b8abfd08c8cd8f55d8e4c05b
-size 6010
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}