Add v1

.gitignore

@@ -0,0 +1,3 @@
+checkpoint-*/
+
+tmp*

README.md

@@ -0,0 +1,66 @@
+---
+language:
+- fr
+pipeline_tag: text-generation
+library_name: transformers
+inference: false
+tags:
+- LLM
+- llama
+- llama-2
+---
+
+<p align="center" width="100%">
+<img src="https://huggingface.co/bofenghuang/vigogne-2-13b-instruct/resolve/main/vigogne_logo.png" alt="Vigogne" style="width: 40%; min-width: 300px; display: block; margin: auto;">
+</p>
+
+# Vigogne-2-13B-Instruct: A Llama-2 based French instruction-following model
+
+Vigogne-2-13B-Instruct is a model based on [LLaMA-2-13B](https://ai.meta.com/llama) that has been fine-tuned to follow French instructions.
+
+For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
+
+**Usage and License Notices**: Vigogne-2-13B-Instruct follows the same usage policy as Llama-2, which can be found [here](https://ai.meta.com/llama/use-policy).
+
+## Usage
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
+from vigogne.preprocess import generate_instruct_prompt
+
+model_name_or_path = "bofenghuang/vigogne-2-13b-instruct"
+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_instruct_prompt(user_query)
+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,
+)
+generated_tokens = generated_outputs.sequences[0, input_length:]
+generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
+print(generated_text)
+```
+
+You can also 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>
+
+## Example Outputs
+
+*todo*
+
+## Limitations
+
+Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers.

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.32.0.dev0"
+}

pytorch_model-00001-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42ef4903a026241831b8e77927cc8769f846945179a7cbc332e993044641a6c9
+size 1947780725

pytorch_model-00002-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1699f542cf38eb6fbd76495dbad3505a3e5652c87a1cd1e63aabf1de551841e
+size 1903237675

pytorch_model-00003-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eac9e924df59601c4da1e175432372a9e7e8006ecf566751660f90f91a66ff4
+size 1903237675

pytorch_model-00004-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee9a8c9f9a57c49276a7cc85c55fe097b9b5c1b44b33c5031de6c6f739712ddf
+size 1903237675

pytorch_model-00005-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1d25a6a258d9f05efb9652d878fd2e6ec5e6925fdf59148ba69c701d08fa89
+size 1903237675

pytorch_model-00006-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52b8786978116ecaff08c4912360f95ee76ecbdd60188fa7b81da8117565df9c
+size 1903237675

pytorch_model-00007-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6e516f2d4971d5bca2b24d812f68047f22cbea63d95dbdfae762552308a9e6
+size 1903237675

pytorch_model-00008-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae846c4b8291740589bd8be14b14142bfc0bb1a5bf810b1391fc7147e7cdb3dc
+size 1903237675

pytorch_model-00009-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3bba226d7b6dbafda32f4b3886ad2b95eb2caba96660608d369722b3e88acd
+size 1903237675

pytorch_model-00010-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0944fb6bb2e1eb5cde4245f9b946f1f6f931a9a6b6b382fa2a858fecd40b90af
+size 1903237675

pytorch_model-00011-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da2c8f5f8bab9fc8a8ae17cd1453b86629a2c18d6b6a24c215f8c54d02ea2f4
+size 1903237675

pytorch_model-00012-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4437080b5dbacf2ad71b53927c91a8cc8d997a5e7cf031b079aaed784ae05de
+size 1903237675

pytorch_model-00013-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8700c136427ad5aa8922a93941b5c9f3099dcd7e3b6bca0c408a9cb1214af501
+size 1903237675

pytorch_model-00014-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25322b38c7448f93f6f679115abe74a00c8cb56b42578235b603ec41c70dd934
+size 1245241071

pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 26031738880
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00014-of-00014.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.norm.weight": "pytorch_model-00014-of-00014.bin"
+  }
+}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}