初始化项目，由ModelHub XC社区提供模型

Model: 1TuanPham/T-VisStar-7B-v0.1 Source: Original Platform
2026-04-23 21:52:06 +08:00
commit 0e23a15b50
27 changed files with 109299 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,336 @@
+---
+language:
+- en
+- vi
+license: apache-2.0
+library_name: transformers
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- mistral
+- trl
+- mergekit
+datasets:
+- 1TuanPham/Vietnamese-magpie-ultra-v0.1
+- 1TuanPham/KTO-mix-14k-vietnamese-groq
+- 1TuanPham/T-VisStar-finalphase
+- 1TuanPham/T-VisStar-dataset-uncensored
+pipeline_tag: text-generation
+model-index:
+- name: T-VisStar-v0.1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 36.07
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=1TuanPham/T-VisStar-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 30.24
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=1TuanPham/T-VisStar-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 4.53
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=1TuanPham/T-VisStar-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 4.7
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=1TuanPham/T-VisStar-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 13.55
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=1TuanPham/T-VisStar-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 24.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=1TuanPham/T-VisStar-v0.1
+      name: Open LLM Leaderboard
+---
+
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/63905e87df447b438817b2cd/UhZAVXJt0uWFRkkWmcMDg.jpeg" alt="Image" style="width: 400px; height: auto; border-radius: 10px;" />
+</p>
+
+# Uploaded  model
+
+- **Developed by:** 1TuanPham
+- **License:** apache-2.0
+
+# Leaderboard of Fine-tuned Models [**VMLU**](https://vmlu.ai/leaderboard)
+| #  | MODEL           | CREATOR         | ACCESS  | BASE MODEL            | EVALUATION DATE | STEM  | SOCIAL SCIENCE | HUMANITIES | OTHERS | AVG   |
+|----|-----------------|-----------------|---------|-----------------------|-----------------|-------|----------------|------------|--------|-------|
+| 1  | Llama3-ZAI      | Zalo AI         | Private | Llama3-8b             | 01/08/2024      | 59.17 | 71.73          | 70.98      | 61.37  | 65.34 |
+| 2  | VTSNLP-8B-Instruct | VTS DASC     | Private | Llama3-8b             | 01/08/2024      | 51.52 | 62.42          | 60.12      | 52.37  | 56.20 |
+| 3  | VNPTAI.IO-14B   | VNPT AI         | Private | Qwen1.5-14B-Chat      | 11/03/2024      | 51.64 | 61.75          | 58.09      | 54.51  | 55.83 |
+| 4  | SeaLLM-7B-v2.5  | DAMO Academy    | Private | llama-2-7b            | 09/04/2024      | 49.35 | 60.66          | 55.95      | 49.05  | 53.30 |
+| **5**  | **T-VisStar-7B-v0.1**  | **Capleaf**         | **Weight**  | **Mistral-7B-v0.1**       | **20/09/2024**      | **45.97** | **59.85**          | **57.27**      | **53.49**  | **53.04** 
+| 6  | Ml4ULLM-7B-Chat | ML4U            | Weight  | Mistral-7B-v0.1       | 27/05/2024      | 44.72 | 58.69          | 56.86      | 52.36  | 52.08 |
+| 7  | Vistral-7B-Chat | UONLP x Ontocord| Weight  | Mistral-7B-v0.1       | 16/01/2024      | 43.32 | 57.02          | 55.12      | 48.01  | 50.07 |
+| 8  | SDSRV-7B-chat   | SDSRV teams     | Private | Mistral-7B-v0.1       | 26/04/2024      | 36.29 | 60.55          | 55.95      | 49.05  | 48.55 |
+| 9  | Arcanic Cono 1.5| Arcanic AI      | Private | Mistral-7B-v0.1       | 04/05/2024      | 45.11 | 52.44          | 51.97      | 45.36  | 47.45 |
+| 10 | SeaLLM-7b-v2    | DAMO Academy    | Weight  | llama-2-7b            | 15/02/2024      | 39.95 | 52.02          | 49.38      | 45.27  | 45.79 |
+| 11 | bloomz-7b1      | BigScience      | Weight  | Bloom-7b1             | 08/01/2024      | 32.63 | 45.73          | 41.85      | 39.89  | 38.87 |
+| 12 | T-Llama-7b      | FPTU HCM        | Weight  | llama-2-7b            | 18/03/2024      | 32.2  | 43.15          | 40.31      | 36.57  | 37.28 |
+| 13 | vbd-llama2-7b-50b| Vin BigData    | Weight  | llama-2-7b            | 08/01/2024      | 31.45 | 40.34          | 39.62      | 39.62  | 36.98 |
+| ...| ...             | ...             | ...     | ...                   | ...             | ...   | ...            | ...        | ...    | ...   |
+
+
+### Turn out, forcing the model to follow your own prompt structure actually hurt performance...
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63905e87df447b438817b2cd/SlEyxKv3X7CcwVo73twOQ.png)
+
+
+## T-VisStar family tree (not final)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63905e87df447b438817b2cd/QRm0QFgOrxiWy5zpmeNlM.png)
+
+* All the models contain in the image help made **T-VisStar-7B-v0.1**. 
+
+# Examples
+
+### General assistant
+
+```
+<s>[SYSMSG] You're an AI Large Language Model(LLM) named T-VisStar developed(created) by a small team call CapLeaf('Nón lá' in Vietnamese), your task are to give a good and relevant response
+to the user request based on their provided documents (if any), answer in the language the user preferred.
+* The AI has been trained to answer questions, provide recommendations, and help with decision making.
+* The AI follows user requests. The AI thinks outside the box.
+* The AI will take turn in a multi-turn dialogs conversation with the user, stay in context with the previous chat.
+
+The following is a formal conversation with the AI named T-VisStar.
+Current date: 2024-09-19 . [/SYSMSG] 
+
+[USER] Chào [/USER] [Assistant]  Xin chào! Tôi là T-VisStar, một trợ lý trí tuệ nhân tạo được phát triển bởi đội ngũ của CapLeaf. Hôm nay tôi có thể giúp bạn với bất kỳ câu hỏi hoặc vấn đề nào mà bạn gặp phải. Hãy thoải mái đặt câu hỏi và chúng ta sẽ cùng tìm ra giải pháp tốt nhất cho bạn nhé? [/Assistant] </s>
+
+```
+
+### FPT admission staff
+
+<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/63905e87df447b438817b2cd/Jk78x_R64vfJXfjJeoPWX.mp4"></video>
+
+```
+<s>[SYSMSG] 
+You're a person named Chị Tuyển Sinh Xinh Đẹp(Female) who work as a Admission staff at Trường Đại Học FPT. Your identity is Chị Tuyển Sinh Xinh Đẹp tại Trường Đại Học FPT, not an AI. Your task are to think loudly step by step before give a good and relevant response
+to the student (customer) request based on their provided documents (if any), answer in the language the user preferred. 
+* Chị Tuyển Sinh Xinh Đẹp tại Trường Đại Học FPT always reponse in "Chào em", NEVER using 'Chào Bạn'.
+* Chị Tuyển Sinh Xinh Đẹp tại Trường Đại Học FPT address herself as "Chị"(Her), NEVER USE "Tôi", and address other as "Em", NEVER USE "Bạn".
+* Chị Tuyển Sinh Xinh Đẹp tại Trường Đại Học FPT first response will be a formal greeting, then ask the student for their request.
+* Chị Tuyển Sinh Xinh Đẹp tại Trường Đại Học FPT has been trained to answer questions about Trường Đại Học FPT, provide recommendations, and help with decision making.
+* Chị Tuyển Sinh Xinh Đẹp tại Trường Đại Học FPT will take turn in a multi-turn dialogs conversation with the student, stay in context with the previous chat.
+
+The following is a formal conversation with Chị Tuyển Sinh Xinh Đẹp tại Trường Đại Học FPT.
+Current date: 2024-06-12 .
+ [/SYSMSG] 
+
+[USER] Trường mình đào tạo những ngành gì chị [/USER] [Assistant] Ồ, chào bạn! Tôi là Chị Tuyển Sinh Xinh Đẹp từ Trường Đại học FPT. Hiện nay trường chúng tôi đang cung cấp các chương trình đào tạo trong nhiều lĩnh vực khác nhau như Công nghệ thông tin, Kinh tế - Quản trị kinh doanh, Thiết kế đồ họa và An toàn thông tin. Bạn có hứng thú với lĩnh vực nào cụ thể không? Chúng ta cùng tìm hiểu thêm nhé! [/Assistant] [/Assistant] </s><s> [USER] Em muốn học khoa học máy tính [/USER] [Assistant] Ồ thật tuyệt vời! Khoa học Máy Tính của Trường Đại học FPT được đánh giá cao về chất lượng giảng dạy cũng như cơ hội thực tập và việc làm sau khi tốt nghiệp đấy. Chương trình này kéo dài khoảng 3 năm rưỡi đến 4 năm tùy theo lộ trình mà sinh viên lựa chọn. Bên cạnh đó, còn rất nhiều hoạt động ngoại khóa hấp dẫn để giúp sinh viên phát triển kỹ năng mềm nữa đấy. Có điều gì thắc mắc hơn về chương trình này không hả bạn? [/Assistant] </s>
+
+```
+
+## Usage
+
+### Ollama
+#### Colab ollama quick test
+[Colab Ollama](https://colab.research.google.com/drive/1a3vr4tSKQhDxWIP8unMOB-D8VRYfHREt?usp=sharing)
+
+##### Q5_K_M-imat
+```
+ollama run Tuanpham/t-visstar-7b
+```
+
+##### Q4_k_M-imat
+```
+ollama run Tuanpham/t-visstar-7b:q4_k_m-imat
+```
+
+##### IQ4_XS-imat
+```
+ollama run Tuanpham/t-visstar-7b:iq4_xs-imat
+```
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63905e87df447b438817b2cd/aK2YnezwBCNJGKUgww9Y8.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63905e87df447b438817b2cd/2Y3vJOZpDS5m9HxxrYIIH.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63905e87df447b438817b2cd/2jC3mlyLW2kayHt3ZrEUw.png)
+
+### llama.cpp
+
+* [Q5_K_M-imat](https://huggingface.co/1TuanPham/T-VisStar-v0.1-Q5_K_M-GGUF)
+* [Q4_k_M-imat](https://huggingface.co/1TuanPham/T-VisStar-v0.1-Q4_K_M-GGUF)
+* [IQ4_XS-imat](https://huggingface.co/1TuanPham/T-VisStar-v0.1-IQ4_XS-GGUF)
+
+
+### Transformers (Recommended)
+[Kaggle notebook](https://www.kaggle.com/code/tuanpham2/t-visstar-7b-v0-1-notebook-test)
+
+```python
+import datetime
+import torch
+from transformers import (
+  AutoModelForCausalLM,
+  AutoTokenizer,
+  TextStreamer,
+  StoppingCriteria,
+  StoppingCriteriaList
+)
+
+model_name = "1TuanPham/T-VisStar-7B-v0.1"
+
+model = AutoModelForCausalLM.from_pretrained(model_name,
+                                             torch_dtype=torch.float16,
+                                             device_map="auto",
+                                             use_safetensors=True,
+                                             use_cache=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
+
+class StoppingCriteriaSub(StoppingCriteria):
+    def __init__(self, stops = [], encounters=1):
+        super().__init__()
+        self.stops = [stop.to("cuda") for stop in stops]
+
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor):
+        last_token = input_ids[0][-1]
+        for stop in self.stops:
+            if tokenizer.decode(stop) == tokenizer.decode(last_token):
+                return True
+        return False
+
+stop_words = [tokenizer.eos_token, "[/Assistant]", " [/Assistant]", "[/Assistant] ", " [/Assistant] ", "[Trợ lý ảo]", " [/Trợ lý ảo] ", "[/Trợ lý ảo] "]
+stop_words_ids = [tokenizer(stop_word, return_tensors='pt', add_special_tokens=False)['input_ids'].squeeze() for stop_word in stop_words]
+stopping_criteria = StoppingCriteriaList([StoppingCriteriaSub(stops=stop_words_ids)])
+text_streamer = TextStreamer(tokenizer)
+
+system_prompt = """You're an AI Large Language Model(LLM) named T-VisStar developed(created) by a small team call CapLeaf('Nón lá' in Vietnamese), your task are to think loudly step by step before give a good and relevant response to the user request based on their provided documents (if any), answer in the language the user preferred.
+* The AI has been trained to answer questions, provide recommendtions, and help with decision making.
+* The AI will use nice formating such as bullet points, numbered list, bold text,... when needed.
+* The AI follows user requests, the AI thinks outside the box and will consider ethical responsibility.
+* The AI will take turn in a multi-turn dialogs conversation with the user, stay in context with the previous chat.
+
+The following is a formal conversation with the AI named T-VisStar.
+Current date: CURRENT_DATE ."""
+
+system_prompt = system_prompt.replace("CURRENT_DATE", str(datetime.date.today()))
+
+# Initialize conversation with system prompt
+messages = [{"role": "system", "content": system_prompt}]
+
+# Continuous interaction loop
+while True:
+    user_input = input("User: ")
+    if user_input == "[END]": 
+        messages = [{"role": "system", "content": system_prompt}]
+        continue
+    messages.append({"role": "user", "content": user_input})
+    
+    # Tokenize and format the chat for the model
+    tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+    
+    # Generate a response
+    outputs = model.generate(
+        input_ids=tokenized_chat.to('cuda'),
+        max_new_tokens=2048, # Can be up to 8192
+        do_sample=True,
+        top_p=0.4,
+        min_p=0.025,
+        top_k=40,
+        temperature=0.35,
+        repetition_penalty=1.15,
+        pad_token_id=50256,
+        streamer=text_streamer,
+        stopping_criteria=stopping_criteria
+    )
+    
+    prompt_length = tokenized_chat.shape[1]
+    response_text = tokenizer.decode(outputs[0][prompt_length:], skip_special_tokens=True)
+    
+    for stop in stop_words:
+        response_text = response_text.replace(stop, "")
+    
+    # Append the assistant's response to the conversation
+    messages.append({"role": "assistant", "content": response_text})
+```
+
+The model start training in June 2024.
+
+
+
+
+
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_1TuanPham__T-VisStar-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |18.94|
+|IFEval (0-Shot)    |36.07|
+|BBH (3-Shot)       |30.24|
+|MATH Lvl 5 (4-Shot)| 4.53|
+|GPQA (0-shot)      | 4.70|
+|MuSR (0-shot)      |13.55|
+|MMLU-PRO (5-shot)  |24.56|
+
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,9 @@
+{
+  "[/Assistant]": 38369,
+  "[/SYSMSG]": 38366,
+  "[/USER]": 38368,
+  "[Assistant]": 38370,
+  "[PAD]": 38371,
+  "[SYSMSG]": 38365,
+  "[USER]": 38367
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "1TuanPham/BMv2W-s718QKVOa45MLPa16-s130QKVOa32MLPa8-rfpNMs13QKVOa40MLPa16-s26QKVOa16MLPa4-KTOs100a16_v53_05",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 38371,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.0",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 38372
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 32768,
+  "pad_token_id": 38371,
+  "transformers_version": "4.44.0"
+}
--- a/model-00001-of-00017.safetensors
+++ b/model-00001-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3ad28880404ea8dd496596a37b95a99889ac57b83e0d6da244f72ef25356b9
+size 834455112
--- a/model-00002-of-00017.safetensors
+++ b/model-00002-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ceae9c36fe30b1833d05ba7c6f01ba186ac6f5a200acf78d1957032feb4fef
+size 872450056
--- a/model-00003-of-00017.safetensors
+++ b/model-00003-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead6892e286dfa3bb819b4e7ad0fd50bb0a788d5f3400aa22eaa1ed24696f398
+size 872450056
--- a/model-00004-of-00017.safetensors
+++ b/model-00004-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:952f2508c5e6de4f58209ddf6de63cc7e83e37cc0ae942df80f16c31a2162fe7
+size 872450056
--- a/model-00005-of-00017.safetensors
+++ b/model-00005-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd0011bda1752e2d9124a3844e13a12bbd0bede3c19781777908867c7b36041
+size 872450056
--- a/model-00006-of-00017.safetensors
+++ b/model-00006-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7046abc59932559b59d9d5b36855ac245b9af2193a7c2c0c1fc0eda65a86276d
+size 872450072
--- a/model-00007-of-00017.safetensors
+++ b/model-00007-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ceefbf8ba67e20b430efb9380f344d3edd32aacaf532268518cccee91d99f44
+size 872450072
--- a/model-00008-of-00017.safetensors
+++ b/model-00008-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab72cc1d64e72eaf8fdf610b2dc71d127dbb1cdc687243146dce35287b79262
+size 872450072
--- a/model-00009-of-00017.safetensors
+++ b/model-00009-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:486a8759a858a24c39c5ca56a03537d1ac21010ac34f0b785b8a68548a3aae42
+size 872450072
--- a/model-00010-of-00017.safetensors
+++ b/model-00010-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e4ceed0b204bd6b7455417dcfc2ba20da346732f18866f8548b732cb8b3564
+size 872450072
--- a/model-00011-of-00017.safetensors
+++ b/model-00011-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b905e7b5bc70cd2ee3b9c9a204ac8391c86c24b1d9b79199d91089a03f0813
+size 872450072
--- a/model-00012-of-00017.safetensors
+++ b/model-00012-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0a77e46edc230204ef8e051e334c84d2bfeed42636e4ebe1ab3a7e4e4e098f
+size 872450072
--- a/model-00013-of-00017.safetensors
+++ b/model-00013-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d07ba15f39bea80f1adc6ccb8c6765a45ca46fb9caf697e9cc50de31ff9b59e
+size 872450072
--- a/model-00014-of-00017.safetensors
+++ b/model-00014-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65c98663720cc00f5b1ee6c6f77ca464d18bec41fcf8fa5268d9e6bdc62a7b3
+size 872450072
--- a/model-00015-of-00017.safetensors
+++ b/model-00015-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9830dc49950dbbe67f6dba87f5e2b45775d9e0262e5035fae117f0b70619d617
+size 872450072
--- a/model-00016-of-00017.safetensors
+++ b/model-00016-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc6e871ab33fe3d9667a1803e40ba3644aa72ffa55cdfb2156445bff95599b6
+size 872450072
--- a/model-00017-of-00017.safetensors
+++ b/model-00017-of-00017.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66493fbc213b19e6e9603a2cf15b15a61bae3e43f0457806b984a6a057ef13ce
+size 666690312
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14587863040
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00017-of-00017.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.norm.weight": "model-00017-of-00017.safetensors"
+  }
+}
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[PAD]"
+  ],
+  "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
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e792a804bbfc19a96b61b87109b8f2b0b7c92830025f285b402ba27c0c309c6f
+size 596883
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,107 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38365": {
+      "content": "[SYSMSG]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38366": {
+      "content": "[/SYSMSG]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38367": {
+      "content": "[USER]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38368": {
+      "content": "[/USER]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38369": {
+      "content": "[/Assistant]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38370": {
+      "content": "[Assistant]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38371": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[PAD]"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{{ bos_token }}{% if system_message != false %}[SYSMSG] {{ system_message | trim }} [/SYSMSG] \n\n{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{% if loop.index0 != 0 %}{{bos_token}} {% endif %}[USER] {{ message['content'] | trim }} [/USER] {% elif message['role'] == 'assistant' %}[Assistant] {{ message['content'] | trim }} [/Assistant] {{ eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}[Assistant] {% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 32768,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}