commit 6fb125bf65ff16322b1d85156aea94044b5421d3 Author: ModelHub XC Date: Tue May 26 08:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/TOI-157-Phi-4-Reasoning-Mini Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9304233 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.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 + +*.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 + +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..512a16a --- /dev/null +++ b/README.md @@ -0,0 +1,94 @@ +--- +license: mit +base_model: +- microsoft/Phi-4-mini-reasoning +language: +- en +pipeline_tag: text-generation +library_name: transformers +tags: +- trl +- text-generation-inference +- math +- code +--- + +![1](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/jhaXgo4VgX-9HbP3wtu7s.png) + +# **TOI-157-Phi-4-Reasoning-Mini** + +> **TOI-157-Phi-4-Reasoning-Mini** is a reasoning-focused model fine-tuned on **Microsoft’s Phi-4-mini-reasoning** for **Edge-level Abliterated Reasoning** and optimized **polished token probabilities**, enhancing balanced **multilingual generation** across mathematics and general-purpose reasoning. +> It specializes in **event-driven logic**, **structured analysis**, and precise probabilistic modeling—making it an ideal tool for researchers, educators, and developers working with uncertainty and structured reasoning. + +## **Key Features** + +1. **Abliterated Reasoning** + Enhanced reasoning precision through polished token probability distributions in Phi-based models, ensuring balanced and context-aware outputs. + +2. **Event Simulation & Logical Analysis** + Models random events, probability-driven reasoning, and logical decision-making with strong consistency. + +3. **Multilingual Mathematical & General-Purpose Problem Solving** + Delivers robust performance in **math**, **probability**, and **structured multilingual tasks**, enabling wide applicability in global research and education. + +4. **Hybrid Symbolic-Probabilistic Thinking** + Combines structured logic, probabilistic inference, and reasoning fluency, providing accuracy across uncertainty-driven tasks. + +5. **Structured Output Mastery** + Generates well-structured outputs in **LaTeX**, **Markdown**, **JSON**, **CSV**, and **YAML**, supporting technical workflows and data-driven research. + +6. **Optimized Lightweight Footprint** + Compact **mini parameter size**, deployable on **edge devices**, **offline clusters**, and **mid-range GPUs**, while maintaining reasoning quality. + +## **Quickstart with Transformers** + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline +torch.random.manual_seed(0) + +model_id = "prithivMLmods/TOI-157-Phi-4-Reasoning-Mini" +model = AutoModelForCausalLM.from_pretrained( + model_id, + device_map="cuda", + torch_dtype="auto", + trust_remote_code=True, +) +tokenizer = AutoTokenizer.from_pretrained(model_id) + +messages = [{ + "role": "user", + "content": "How to solve 3*x^2 + 4*x + 5 = 1?" +}] +inputs = tokenizer.apply_chat_template( + messages, + add_generation_prompt=True, + return_dict=True, + return_tensors="pt", +) + +outputs = model.generate( + **inputs.to(model.device), + max_new_tokens=32768, + temperature=0.8, + top_p=0.95, + do_sample=True, +) +outputs = tokenizer.batch_decode(outputs[:, inputs["input_ids"].shape[-1]:]) + +print(outputs[0]) +``` + +## **Intended Use** + +* Balanced multilingual reasoning and probability modeling +* Event simulation, uncertainty analysis, and structured problem solving +* Educational and research-focused reasoning tasks +* Lightweight deployment in constrained environments +* Technical content and structured data generation + +## **Limitations** + +* Focused on reasoning and mathematics—less suited for creative writing +* Smaller size may limit depth on highly complex, multi-step tasks +* Prioritizes structured reasoning and probabilistic accuracy over conversational or emotional tone. \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..af52cde --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,12 @@ +{ + "<|/tool_call|>": 200026, + "<|/tool|>": 200024, + "<|assistant|>": 200019, + "<|end|>": 200020, + "<|system|>": 200022, + "<|tag|>": 200028, + "<|tool_call|>": 200025, + "<|tool_response|>": 200027, + "<|tool|>": 200023, + "<|user|>": 200021 +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..3a3cd53 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1 @@ +{{ '<|system|>Your name is Phi, an AI math expert developed by Microsoft.' }}{% for message in messages %}{% if message['role'] == 'system' %} {{ message['content'] }}{% if 'tools' in message and message['tools'] is not none %}{{ '<|tool|>' + message['tools'] + '<|/tool|>' }}{% endif %}{% endif %}{% endfor %}{{ '<|end|>' }}{% for message in messages %}{% if message['role'] != 'system' %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..66bb3aa --- /dev/null +++ b/config.json @@ -0,0 +1,138 @@ +{ + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 199999, + "dtype": "float16", + "embd_pdrop": 0.0, + "eos_token_id": 199999, + "full_attn_mod": 1, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "interpolate_factor": 1, + "lm_head_bias": false, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "phi3", + "num_attention_heads": 24, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "original_max_position_embeddings": 4096, + "pad_token_id": 199999, + "partial_rotary_factor": 0.75, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "long_factor": [ + 1, + 1.118320672, + 1.250641126, + 1.398617824, + 1.564103225, + 1.74916897, + 1.956131817, + 2.187582649, + 2.446418898, + 2.735880826, + 3.059592084, + 3.421605075, + 3.826451687, + 4.279200023, + 4.785517845, + 5.351743533, + 5.984965424, + 6.693110555, + 7.485043894, + 8.370679318, + 9.36110372, + 10.4687158, + 11.70738129, + 13.09260651, + 14.64173252, + 16.37415215, + 18.31155283, + 20.47818807, + 22.90118105, + 25.61086418, + 28.64115884, + 32.03, + 32.1, + 32.13, + 32.23, + 32.6, + 32.61, + 32.64, + 32.66, + 32.7, + 32.71, + 32.93, + 32.97, + 33.28, + 33.49, + 33.5, + 44.16, + 47.77 + ], + "short_factor": [ + 1, + 1.118320672, + 1.250641126, + 1.398617824, + 1.564103225, + 1.74916897, + 1.956131817, + 2.187582649, + 2.446418898, + 2.735880826, + 3.059592084, + 3.421605075, + 3.826451687, + 4.279200023, + 4.785517845, + 5.351743533, + 5.984965424, + 6.693110555, + 7.485043894, + 8.370679318, + 9.36110372, + 10.4687158, + 11.70738129, + 13.09260651, + 14.64173252, + 16.37415215, + 18.31155283, + 20.47818807, + 22.90118105, + 25.61086418, + 28.64115884, + 32.03, + 32.1, + 32.13, + 32.23, + 32.6, + 32.61, + 32.64, + 32.66, + 32.7, + 32.71, + 32.93, + 32.97, + 33.28, + 33.49, + 33.5, + 44.16, + 47.77 + ], + "type": "longrope" + }, + "rope_theta": 10000.0, + "sliding_window": 262144, + "tie_word_embeddings": true, + "transformers_version": "4.56.2", + "use_cache": true, + "vocab_size": 200064 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "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..053aa9a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "bos_token_id": 199999, + "eos_token_id": [ + 200020, + 199999 + ], + "pad_token_id": 199999, + "transformers_version": "4.56.2" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..439c8df --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:856ce61180bb689282eed6b3a6838bb1f438399be23aefe9d20eb379791fb4ad +size 2418348 diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..02d6d9f --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28dd58aa6c861a521769ba08487e44533e0b1ca95849447506deeae6710f0e26 +size 4903637600 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..d81943b --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5d0564d2b382f656712bec8de199e5bbfcef1490be546d2e8e01450f9563504 +size 2768428424 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d9e951f --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,202 @@ +{ + "metadata": { + "total_parameters": 3836021760, + "total_size": 7672043520 + }, + "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_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.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.qkv_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_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.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.qkv_proj.weight": "model-00002-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_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.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.qkv_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_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.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.qkv_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_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.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.qkv_proj.weight": "model-00001-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_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.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.qkv_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_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.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..156262f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..3a12dac --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea +size 15524095 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..84679d4 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,115 @@ +{ + "add_bos_token": false, + "add_eos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "199999": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200018": { + "content": "<|endofprompt|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200019": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": true + }, + "200020": { + "content": "<|end|>", + "lstrip": false, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": true + }, + "200021": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": true + }, + "200022": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": true + }, + "200023": { + "content": "<|tool|>", + "lstrip": false, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": false + }, + "200024": { + "content": "<|/tool|>", + "lstrip": false, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": false + }, + "200025": { + "content": "<|tool_call|>", + "lstrip": false, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": false + }, + "200026": { + "content": "<|/tool_call|>", + "lstrip": false, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": false + }, + "200027": { + "content": "<|tool_response|>", + "lstrip": false, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": false + }, + "200028": { + "content": "<|tag|>", + "lstrip": false, + "normalized": false, + "rstrip": true, + "single_word": false, + "special": true + } + }, + "bos_token": "<|endoftext|>", + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": {}, + "max_length": 1024, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "stride": 0, + "tokenizer_class": "GPT2Tokenizer", + "truncation_side": "right", + "truncation_strategy": "longest_first", + "unk_token": "<|endoftext|>" +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..2460dac --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cb65a857824fa6615bb1782d95d882617a8bbce1da0317118586b36f39e98bd +size 3910310