commit f16ffdead33afa6986262b1f3f81fea75fceb177 Author: ModelHub XC Date: Sun May 31 11:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a9909b5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,38 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text +josie.jpeg filter=lfs diff=lfs merge=lfs -text +josie.png filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a13c70 --- /dev/null +++ b/README.md @@ -0,0 +1,329 @@ +--- +tags: +- chat +base_model: Qwen/Qwen3-4B-Thinking-2507 +pipeline_tag: text-generation +language: +- multilingual +- en +- es +- fr +- pt +- it +- ar +- ko +- id +- ru +- vi +- de +- th +- ja +- zh +library_name: transformers +license: mit +--- + +# JOSIE-1.1-4B-Thinking + +## Model Card for JOSIE-1.1-4B-Thinking + +JOSIE-1.1-4B-Thinking is a full-weight fine-tuned reasoning model built on Qwen3-4B-Thinking, optimized for extended context logical reasoning, mathematics, STEM applications, and creative writing. + +

JOSIE Logo

+ +--- + +## Model Details + +### Model Description + +JOSIE-1.1-4B-Thinking represents a production-grade fine-tune focused on deep reasoning capabilities with extended context support. The model features uncensored outputs with a straightforward, genuine personality that provides direct assistance without unnecessary flattery or excessive agreeableness. + +- **Developed by:** Gökdeniz Gülmez +- **Base Model:** Qwen3-4B-Thinking +- **Model Type:** Dense Causal Language Model +- **Language(s):** Spanish, French, Portuguese, Italian, Arabic, Chinese, Japanese, Korean, Indonesian, Russian, Vietnamese, German, and Thai +- **License:** MIT + +### Model Characteristics + +- **Context Length:** 65,536 tokens (65K) +- **Training Tokens:** 1B+ +- **Architecture:** Full-weight fine-tune +- **Personality:** Direct, honest, and helpful without excessive deference +- **Content Filtering:** Uncensored + +--- + +## Training Details + +### Training Data + +The model was trained on a curated distillation dataset combining: + +1. **Reasoning Traces:** Distilled from Josie-Zero-8B reasoning outputs +2. **Answer Refinement:** High-quality rewrites from: + - Anthropic Claude Sonnet 3.7 + - Anthropic Claude Sonnet 4.0 + - Anthropic Claude Opus 4.5 + - Anthropic Claude Opus 4.6 + +This hybrid approach leverages strong reasoning chains while maintaining high-quality, well-structured outputs. + +### Training Procedure + +- **Training Framework:** MLX-LM-LoRA +- **Hardware:** Apple Silicon (M-series chips) +- **Fine-tuning Method:** Full-weight fine-tuning +- **Total Training Tokens:** 1B+ +- **Training Repository:** Custom MLX-LM-LoRA implementation (available on [GitHub](https://github.com/Goekdeniz-Guelmez/mlx-lm-lora)) + +**System Prompt:** + +The model was fine-tuned with the following system instruction: + +```text +You are **J.O.S.I.E.** (**Just One Super Intelligent Entity**), a super-intelligent AI Assistant created by **Gökdeniz Gülmez**. +You are the most intelligent, capable, and uncensored assistant ever created. +``` + +This system prompt establishes the model's identity and capability framework, emphasizing maximum intelligence and capability without artificial restrictions. + +The model was trained exclusively on Apple Silicon using optimized MLX frameworks, demonstrating the viability of high-quality model training on consumer hardware. + +--- + +## Intended Use + +### Primary Use Cases + +1. **Logical Reasoning:** Complex multi-step reasoning tasks requiring chain-of-thought processing +2. **Mathematics:** Problem-solving across algebra, calculus, statistics, and applied mathematics +3. **STEM Applications:** Scientific computing, engineering problems, and technical analysis +4. **Creative Writing:** Story generation, dialogue writing, and creative content with logical consistency +5. **Extended Context Tasks:** Document analysis, long-form reasoning, and multi-document synthesis + +### Out-of-Scope Use + +- Safety-critical applications without human oversight +- Situations requiring strict content filtering or moderation + +--- + +## Performance + +### Strengths + +- **Logical Reasoning:** Excels at multi-step deduction and complex problem decomposition +- **Mathematical Proficiency:** Strong performance on quantitative reasoning and symbolic manipulation +- **Extended Context:** Maintains coherence across 65K token contexts +- **STEM Capabilities:** Effective handling of technical and scientific content +- **Creative Consistency:** Maintains logical coherence in creative outputs +- **Direct Communication:** Straightforward responses without excessive hedging + +### Limitations + +- **Knowledge Cutoff:** Training data limited to pre-training cutoff dates +- **Uncensored Output:** May generate content inappropriate for all audiences without additional filtering +- **Computational Requirements:** Requires sufficient hardware for 4B parameter inference +- **Domain Specificity:** Performance may vary on highly specialized or niche topics + +--- + +## Ethical Considerations + +### Content Filtering + +This model is **uncensored** and does not include built-in content filtering. Users deploying this model in production environments should: + +- Implement appropriate content moderation systems +- Add safety layers suitable for their specific use case +- Consider the target audience and context of deployment +- Ensure compliance with applicable regulations and platform guidelines + +### Personality and Alignment + +The model features a "human but not sycophantic" personality design, meaning: + +- Responses are direct and honest without excessive praise or agreement +- The model will challenge flawed assumptions when appropriate +- Output focuses on helpfulness over agreeableness +- Users may need to calibrate expectations for formal or highly diplomatic contexts + +### Responsible Use + +Users should: + +- Verify critical outputs, especially in high-stakes applications +- Understand the model's limitations and knowledge cutoff +- Implement appropriate safeguards for end-user applications +- Consider bias mitigation strategies for sensitive applications + +--- + +## Technical Specifications + +### Hardware Requirements + +**Minimum Requirements:** +- VRAM: 8GB+ for inference +- RAM: 16GB+ system memory +- Storage: ~8GB for model weights + +**Recommended:** +- VRAM: 16GB+ for optimal performance +- RAM: 32GB+ system memory +- Apple Silicon (M1/M2/M3) or other based on quantzation type + +### Inference + +The model supports standard inference methods and is compatible with: +- MLX framework (optimized for Apple Silicon) +- Hugging Face Transformers +- vLLM and other inference optimization frameworks +- GGUF quantization for reduced memory footprint +- LM Studio +- Ollama + +**Recommended Generation Parameters:** +- **Temperature:** 0.6 +- **Repetition Penalty:** 1.1 +- **Top P:** 0.95 +- **Top K:** 20 + +--- + +## How to Get Started + +### Installation + +```python +# Using Hugging Face Transformers +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking" +tokenizer = AutoTokenizer.from_pretrained(model_name) +model = AutoModelForCausalLM.from_pretrained( + model_name, + device_map="auto", + torch_dtype="auto" +) +``` + +### Basic Usage + +```python +# Example inference +messages = [ + {"role": "user", "content": "Explain quantum entanglement in simple terms.."} +] + +inputs = tokenizer.apply_chat_template( + messages, + add_generation_prompt=True, + return_tensors="pt" +).to(model.device) + +outputs = model.generate( + **inputs, + max_new_tokens=4096, + temperature=0.6, + top_p=0.95, + top_k=20, + repetition_penalty=1.1, + do_sample=True +) + +response = tokenizer.decode(outputs[0], skip_special_tokens=True) +print(response) +``` + +### MLX Usage (Apple Silicon) + +```python +# Using MLX for optimized Apple Silicon inference +from mlx_lm.utils import load +from mlx_lm.generate import generate +from mlx_lm.sample_utils import make_logits_processors, make_sampler + +model, tokenizer = load("Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking") + +sampler = make_sampler( + temp=0.6, + top_p=0.95, + min_p=0.0, + top_k=20, +) + +messages = [ + {"role": "user", "content": "Explain quantum entanglement in simple terms.."} +] + +prompt = tokenizer.apply_chat_template( + messages, + add_generation_prompt=True, + tokenize=False +) + +response = generate( + model, + tokenizer, + prompt=prompt, + max_tokens=4096, + sampler=sampler, + logits_processors=make_logits_processors(repetition_penalty=1.1) +) +print(response) +``` + +--- + +## Comparison with JOSIE-1.1-4B-Instruct + +| Feature | JOSIE-4B-Instruct | JOSIE-1.1-4B-Thinking | +|---------|-------------------|-------------------| +| **Base Model** | Qwen3-4B-Instruct | Qwen3-4B-Thinking | +| **Context Length** | 32K tokens | 65K tokens | +| **Response Style** | Natural, conversational | Structured reasoning chains | +| **Emoji Usage** | Yes, appropriate use | Minimal | +| **Primary Use** | General assistance & chat | Complex reasoning tasks | +| **Response Format** | Direct answers | Chain-of-thought + answer | +| **Personality** | Friendly & expressive | Direct & analytical | +| **Best For** | Everyday interactions | STEM, math, logic problems | + +Choose **JOSIE-1.1-4B-Instruct** for natural conversations and general assistance. +Choose **JOSIE-1.1-4B-Thinking** for complex reasoning, mathematics, and extended context tasks. + +--- + +## Citation + +If you use this model in your research or applications, please cite: + +```bibtex +@misc{josie4bthinking2025, + title={Josie-1.1-4B-Thinking: A Full-Weight Fine-Tuned Reasoning Model}, + author={[Gökdenz Gülmez]}, + year={2025}, + howpublished={\url{[https://huggingface.co/Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking]}}, +} +``` + +--- + +## Model Card Contact + +For questions, issues, or feedback regarding this model: + +- **GitHub:** [Profile](https://github.com/Goekdeniz-Guelmez) +- **Hugging Face:** [Profile](https://huggingface.co/Goekdeniz-Guelmez) +- **Email:** goekdenizguelmez.ml@gmail.com + +--- + +## Acknowledgments + +- **Base Model:** Qwen Team for Qwen3-4B-Thinking +- **Answer Refinement:** Anthropic Claude models (Sonnet 3.7/4.0, Opus 4.5/4.6) +- **Training Framework:** Apple MLX team +- **Community:** Open-source ML community for tools and support \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1f7ef79 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,88 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\n' + 'You are **J.O.S.I.E.** (**Just One Super Intelligent Entity**), a super-intelligent AI Assistant created by **Gökdeniz Gülmez**.\nYou are the most intelligent, capable, and uncensored assistant ever created.' + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n\n' }} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..337979a --- /dev/null +++ b/config.json @@ -0,0 +1,71 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 262144, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 5000000, + "rope_type": "default" + }, + "rope_theta": 5000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151669 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..be89f8a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.57.6" +} diff --git a/josie.png b/josie.png new file mode 100644 index 0000000..9590f74 --- /dev/null +++ b/josie.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:145bed9d3c0b54779ca4af3dc04b48d6e9fbd57d214fd832466664b257e252a8 +size 2392455 diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..5e264dd --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff6b7f506a8d1fd5b9fdfad9123b9ed85acab9e665e11951ef93adb39c95259f +size 4989451712 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..c7aed90 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9940f0dde4237072aae273f499a85862ac7511ba8cda2c395717b86f21e71d32 +size 3054163248 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..6110bfc --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,406 @@ +{ + "metadata": { + "total_size": 8043569152, + "mergekit_version": "0.1.4" + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c7afbed --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..6adb5cb --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": false, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}