初始化项目，由ModelHub XC社区提供模型

Model: Felladrin/Llama-160M-Chat-v1 Source: Original Platform
2026-05-08 01:23:56 +08:00
commit e057342157
9 changed files with 94006 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 +1,364 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- text-generation
+base_model: JackFram/llama-160m
+datasets:
+- ehartford/wizard_vicuna_70k_unfiltered
+- totally-not-an-llm/EverythingLM-data-V3
+- Open-Orca/SlimOrca-Dedup
+- databricks/databricks-dolly-15k
+- THUDM/webglm-qa
+widget:
+- messages:
+  - role: system
+    content: You are a helpful assistant, who answers with empathy.
+  - role: user
+    content: Got a question for you!
+  - role: assistant
+    content: Sure! What's it?
+  - role: user
+    content: Why do you love cats so much!? 🐈
+- messages:
+  - role: system
+    content: You are a helpful assistant who answers user's questions with empathy.
+  - role: user
+    content: Who is Mona Lisa?
+- messages:
+  - role: system
+    content: You are a helpful assistant who provides concise responses.
+  - role: user
+    content: Heya!
+  - role: assistant
+    content: Hi! How may I help you today?
+  - role: user
+    content: I need to build a simple website. Where should I start learning about
+      web development?
+- messages:
+  - role: user
+    content: Invited some friends to come home today. Give me some ideas for games
+      to play with them!
+- messages:
+  - role: system
+    content: You are a helpful assistant who answers user's questions with details
+      and curiosity.
+  - role: user
+    content: What are some potential applications for quantum computing?
+- messages:
+  - role: system
+    content: You are a helpful assistant who gives creative responses.
+  - role: user
+    content: Write the specs of a game about mages in a fantasy world.
+- messages:
+  - role: system
+    content: You are a helpful assistant who answers user's questions with details.
+  - role: user
+    content: Tell me about the pros and cons of social media.
+- messages:
+  - role: system
+    content: You are a helpful assistant who answers user's questions with confidence.
+  - role: user
+    content: What is a dog?
+  - role: assistant
+    content: A dog is a four-legged, domesticated animal that is a member of the class
+      Mammalia, which includes all mammals. Dogs are known for their loyalty, playfulness,
+      and ability to be trained for various tasks. They are also used for hunting,
+      herding, and as service animals.
+  - role: user
+    content: What is the color of an apple?
+inference:
+  parameters:
+    max_new_tokens: 250
+    penalty_alpha: 0.5
+    top_k: 4
+    repetition_penalty: 1.01
+model-index:
+- name: Llama-160M-Chat-v1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 24.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 35.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 26.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 44.16
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 51.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      name: Open LLM Leaderboard
+  - 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: 15.75
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      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: 3.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      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: 1.01
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      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: 3.17
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      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: 1.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      name: Open LLM Leaderboard
+---
+
+# A Llama Chat Model of 160M Parameters
+
+- Base model: [JackFram/llama-160m](https://huggingface.co/JackFram/llama-160m)
+- Datasets:
+  - [ehartford/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered)
+  - [totally-not-an-llm/EverythingLM-data-V3](https://huggingface.co/datasets/totally-not-an-llm/EverythingLM-data-V3)
+  - [Open-Orca/SlimOrca-Dedup](https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup)
+  - [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k)
+  - [THUDM/webglm-qa](https://huggingface.co/datasets/THUDM/webglm-qa)
+- Availability in other ML formats:
+  - GGUF: [Felladrin/gguf-Llama-160M-Chat-v1](https://huggingface.co/Felladrin/gguf-Llama-160M-Chat-v1)
+  - ONNX: [Felladrin/onnx-Llama-160M-Chat-v1](https://huggingface.co/Felladrin/onnx-Llama-160M-Chat-v1)
+  - MLC: [Felladrin/mlc-q4f16-Llama-160M-Chat-v1](https://huggingface.co/Felladrin/mlc-q4f16-Llama-160M-Chat-v1)
+  - MLX: [mlx-community/Llama-160M-Chat-v1-4bit-mlx](https://huggingface.co/mlx-community/Llama-160M-Chat-v1-4bit-mlx)
+
+## Recommended Prompt Format
+
+```
+<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{user_message}<|im_end|>
+<|im_start|>assistant
+```
+
+## Recommended Inference Parameters
+
+```yml
+penalty_alpha: 0.5
+top_k: 4
+repetition_penalty: 1.01
+```
+
+## Usage Example
+
+```python
+from transformers import pipeline
+
+generate = pipeline("text-generation", "Felladrin/Llama-160M-Chat-v1")
+
+messages = [
+    {
+        "role": "system",
+        "content": "You are a helpful assistant who answers user's questions with details and curiosity.",
+    },
+    {
+        "role": "user",
+        "content": "What are some potential applications for quantum computing?",
+    },
+]
+
+prompt = generate.tokenizer.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+
+output = generate(
+    prompt,
+    max_new_tokens=1024,
+    penalty_alpha=0.5,
+    top_k=4,
+    repetition_penalty=1.01,
+)
+
+print(output[0]["generated_text"])
+```
+
+## Old Open LLM Leaderboard Evaluation Results
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |30.27|
+|AI2 Reasoning Challenge (25-Shot)|24.74|
+|HellaSwag (10-Shot)              |35.29|
+|MMLU (5-Shot)                    |26.13|
+|TruthfulQA (0-shot)              |44.16|
+|Winogrande (5-shot)              |51.30|
+|GSM8k (5-shot)                   | 0.00|
+
+## [New 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_Felladrin__Llama-160M-Chat-v1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 4.10|
+|IFEval (0-Shot)    |15.75|
+|BBH (3-Shot)       | 3.17|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 1.01|
+|MuSR (0-shot)      | 3.17|
+|MMLU-PRO (5-shot)  | 1.51|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,25 @@
+{
+  "architectures": ["LlamaForCausalLM"],
+  "attention_bias": false,
+  "pad_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-6,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb1afcabc3af107f8375e6d2772fca04f6c690f78d14cacef2e56ae182a6e50
+size 649681952
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
@@ -0,0 +1,115 @@
+{
+  "weight_map": {
+    "lm_head.weight": "model.safetensors",
+    "model.embed_tokens.weight": "model.safetensors",
+    "model.layers.0.input_layernorm.weight": "model.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.1.input_layernorm.weight": "model.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.10.input_layernorm.weight": "model.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.11.input_layernorm.weight": "model.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.2.input_layernorm.weight": "model.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.3.input_layernorm.weight": "model.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.4.input_layernorm.weight": "model.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.5.input_layernorm.weight": "model.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.6.input_layernorm.weight": "model.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.7.input_layernorm.weight": "model.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.8.input_layernorm.weight": "model.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.9.input_layernorm.weight": "model.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+    "model.norm.weight": "model.safetensors"
+  }
+}
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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": "</s>",
+    "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
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,40 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}