commit f4d0d6797ee8922afb4a41e105dbced1be934a56 Author: ModelHub XC Date: Sun Aug 30 20:53:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/Eratosthenes-Polymath-14B-Instruct Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..615066e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm 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 +model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8062d2f --- /dev/null +++ b/README.md @@ -0,0 +1,122 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Qwen/Qwen2.5-14B-Instruct +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +- coder +- Math +- RL +--- + +![8.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/HXno2Of6OWRexX88f2wtL.png) + +# **Eratosthenes-Polymath-14B-Instruct** + +> **Eratosthenes-Polymath-14B-Instruct** is built on the Qwen 2.5 14B modality architecture, engineered to excel in mathematical reasoning, distributed reinforcement learning (RL), and general-purpose problem solving. This model is fine-tuned with chain-of-thought reasoning datasets, optimization-focused corpora, and advanced structured reasoning datasets to maximize its capabilities in logical deduction, multi-step reasoning, and intelligent decision-making. + +## **Key Improvements** +1. **Advanced Mathematical Reasoning**: + Excels in solving complex equations, performing symbolic computation, theorem proving, and step-by-step mathematical problem-solving. + +2. **Distributed Reinforcement Learning Expertise**: + Specially fine-tuned for robust policy optimization using distributed RL techniques, providing resilience and optimality across dynamic problem spaces. + +3. **General-Purpose Reasoning and Problem Solving**: + Strong across a broad range of domains, handling factual questions, logical analysis, and multi-step cognitive tasks. + +4. **Long-Context Mastery**: + Supports up to 128K tokens for context and can generate up to 8K tokens, enabling detailed, coherent long-form outputs and complex derivations. + +5. **Superior Instruction Following**: + Capable of following complex and structured prompts precisely, maintaining focus and clarity over extended dialogues. + +6. **Coding and Algorithmic Fluency**: + Highly effective in code generation, debugging, algorithm design, and optimization problem modeling across various programming languages. + +## **Quickstart with transformers** + +Use the model easily with the `transformers` library and `apply_chat_template`: + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "prithivMLmods/Eratosthenes-Polymath-14B-Instruct" + +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype="auto", + device_map="auto" +) +tokenizer = AutoTokenizer.from_pretrained(model_name) + +prompt = "Explain the connection between distributed reinforcement learning and robust policy optimization." +messages = [ + {"role": "system", "content": "You are an expert assistant specializing in mathematics, optimization, and reinforcement learning."}, + {"role": "user", "content": prompt} +] +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True +) +model_inputs = tokenizer([text], return_tensors="pt").to(model.device) + +generated_ids = model.generate( + **model_inputs, + max_new_tokens=512 +) +generated_ids = [ + output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) +] + +response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] +``` + +## **Intended Use** +1. **Mathematical and Optimization Problem Solving**: + Designed for solving complex mathematical problems, optimization modeling, symbolic logic, and structured derivations. + +2. **Distributed Reinforcement Learning Research**: + Supports designing, analyzing, and explaining distributed RL systems, robust policy optimization, and autonomous decision systems. + +3. **General Knowledge and Reasoning**: + Effective in answering a wide range of questions and performing structured reasoning across scientific, technical, and educational domains. + +4. **Educational and Research Support**: + Ideal for students, researchers, and professionals seeking detailed explanations, derivations, and robust scientific insights. + +5. **Code Writing and Algorithm Design**: + Excels at creating, optimizing, and explaining algorithms, particularly those relevant to mathematical computation and optimization. + +6. **Intelligent Conversational Systems**: + Perfect for technical conversational agents and educational bots requiring deep understanding and detailed reasoning capabilities. + +7. **Long-Form Technical Content Generation**: + Capable of producing structured, coherent articles, tutorials, and research papers, especially in technical and mathematical fields. + +8. **Structured Data Generation**: + Supports outputting structured formats such as proofs, equations, tables, and JSON useful for scientific and technical workflows. + +## **Limitations** +1. **Heavy Hardware Requirements**: + Due to its large parameter count and long-context handling, it requires powerful GPUs or TPUs with significant memory. + +2. **Potential for Training Biases**: + Outputs may still reflect biases from the mathematical, technical, or optimization-specific datasets used during training. + +3. **Less Effective in Creative Tasks**: + Focused more on technical and logical reasoning than on freeform creative writing or storytelling. + +4. **No Real-Time Event Awareness**: + Limited to knowledge prior to its training cutoff, without access to live or real-world updates. + +5. **Prompt Sensitivity**: + Performance may vary based on the clarity, structure, and specificity of the prompt, particularly for complex multi-step tasks. + +6. **Error Propagation Risk**: + Small inaccuracies in early stages of long-form outputs could propagate, affecting the overall answer coherence. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a660a1d --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 131072, + "max_window_layers": 48, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 48, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..c02783a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "eos_token_id": 151643, + "do_sample": true, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "4.51.3" +} diff --git a/model-00001-of-00006.safetensors b/model-00001-of-00006.safetensors new file mode 100644 index 0000000..bc0218d --- /dev/null +++ b/model-00001-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ac01d7940e2f6afd9617e7e062a88fb9c368e0d8caf66660c35a8d67e23b0c6 +size 4907454960 diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors new file mode 100644 index 0000000..aa2910e --- /dev/null +++ b/model-00002-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efcc6f519a8cf9f4c66992e9f64e68318cc1791050c76d891e290225594851cb +size 4954847384 diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors new file mode 100644 index 0000000..0d2439a --- /dev/null +++ b/model-00003-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8358a855ef1056ba7d7725288a10e7615e8c99e89212d1be9e1fc5ae8406c48f +size 4954847376 diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors new file mode 100644 index 0000000..4bcad94 --- /dev/null +++ b/model-00004-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99a825ab16e96f4fbcd4b1e6f71c18dd1e56085ab96f9d3528cd534144b00632 +size 4954847376 diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors new file mode 100644 index 0000000..2a7db27 --- /dev/null +++ b/model-00005-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d526a776ec6e66ba79d652467f30f21d51acf2c77214321223a1be95a99ecb6 +size 4954847376 diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors new file mode 100644 index 0000000..a87cf3e --- /dev/null +++ b/model-00006-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4374aec9fdbeaf1461188bd524e7c0d90de5f12de7f943c6eaa73641e8c729a3 +size 4813289432 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..0c59ebb --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"lm_head.weight": "model-00001-of-00006.safetensors", "model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors"}} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..8e71bf3 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88145e3c3249adc2546ede277e9819d6e405e19072456e4b521cbc724bd60773 +size 7031660 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9967ff3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,35 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "legacy": true, + "model_max_length": 16384, + "pad_token": { + "__type": "AddedToken", + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "sp_model_kwargs": {}, + "unk_token": null, + "tokenizer_class": "LlamaTokenizerFast", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}" +} \ No newline at end of file