commit 4b45599a57c77e2548ae41f769914c433e4e378a Author: ModelHub XC Date: Sat Jun 13 10:41:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fb4224f --- /dev/null +++ b/README.md @@ -0,0 +1,322 @@ +--- +library_name: transformers +pipeline_tag: text-generation +license: apache-2.0 +language: + - en +base_model: Qwen/Qwen3-0.6B +datasets: + - 0xZee/dataset-CoT-Advanced-Calculus-268 + - 0xZee/dataset-CoT-Modern-Physics-177 + - 0xZee/dataset-CoT-Theoretical-Mechanics-307 + - 0xZee/dataset-CoT-Linear-Algebra-667 + - 0xZee/dataset-CoT-Electromagnetism-580 + - 0xZee/dataset-CoT-Molecular-Biology-71 + - 0xZee/dataset-CoT-Physiology-114 + - 0xZee/dataset-CoT-Classical-Mechanics-343 + - 0xZee/dataset-CoT-Differential-Equations-636 + - 0xZee/dataset-CoT-Physics-2254 + - 0xZee/dataset-CoT-Engineering-574 + - 0xZee/dataset-CoT-mathematics + - Alignment-Lab-AI/Lawyer-Instruct +tags: + - causal-lm + - text-generation + - distillation + - knowledge-distillation + - sft + - reasoning + - chain-of-thought + - mathematics + - physics + - engineering + - legal + - stem + - convergentintel + - edge +--- + +# Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT + +A 0.6B parameter model built in two stages: knowledge distillation from a 30B Thinking teacher to establish a structured reasoning backbone, then supervised fine-tuning on legal instruction data. 50x compression. Under 500MB quantized. Runs on a phone. + +The training order is the thesis: teach the model *how to reason* first (distillation from Thinking teacher), then teach it *what to reason about* (legal SFT). The Thinking teacher's extended deliberation traces transfer deeper reasoning structure than an Instruct teacher — critical when the student has only 0.6B parameters to work with. + +> *"Structure beats scale, collaboration beats hierarchy, observation beats theory."* +> — Convergent Intelligence LLC: Research Division + +## Training Pipeline + +### Stage 1: Knowledge Distillation (STEM Reasoning Backbone) + +Qwen3-0.6B distilled from [Qwen3-30B-A3B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507) — a Mixture-of-Experts model with 30B total parameters, ~3B active per token, using the Thinking variant that generates extended internal reasoning traces. + +**Why the Thinking teacher matters at 0.6B:** The Thinking variant produces higher-entropy softmax distributions than the Instruct variant — it considers more reasoning paths before committing. At distillation temperature T=2.0, the 0.6B student sees a richer landscape of alternative derivation strategies. With only 0.6B parameters, every bit of transferred structure counts. The Thinking teacher gives more. + +**Data:** 6,122 STEM chain-of-thought samples across 12 domains: + +| Domain | Samples | +|---|---| +| Physics | 2,254 | +| Linear Algebra | 667 | +| Differential Equations | 636 | +| Electromagnetism | 580 | +| Mathematics | 576 | +| Engineering | 574 | +| Classical Mechanics | 343 | +| Theoretical Mechanics | 307 | +| Advanced Calculus | 268 | +| Modern Physics | 177 | +| Physiology | 114 | +| Molecular Biology | 71 | + +All from [0xZee](https://huggingface.co/0xZee). Shuffled seed 42, split 95/5 train/eval. + +**Loss function:** + +1. **Proof-Weighted Cross-Entropy (55%)** — 2.5x weight on derivation tokens, decaying to 1.5x. Forces the student to allocate its limited capacity to reasoning steps, not answer formatting. +2. **Knowledge Distillation KL Divergence (45%)** — T=2.0, scaled by T². Transfers the Thinking teacher's full deliberation landscape. + +**Training format:** + +``` +Solve the following problem carefully and show a rigorous derivation. + +Problem: +{question} + +Proof: +{CoT} + +Final Answer: +{response} +``` + +**Stage 1 hyperparameters:** + +| Parameter | Value | +|---|---| +| Epochs | 1 | +| Training samples | 5,815 | +| Effective batch size | 8 | +| Learning rate | 1.5e-5 → 1e-6 (cosine) | +| Temperature | 2.0 | +| Proof weight | 2.5 → 1.5 | +| Precision | bf16 | + +--- + +### Stage 2: Supervised Fine-Tuning (Legal Domain) + +The distilled model was fine-tuned on [Alignment-Lab-AI/Lawyer-Instruct](https://huggingface.co/datasets/Alignment-Lab-AI/Lawyer-Instruct) using TRL's SFTTrainer. + +**Why legal on top of STEM:** Legal reasoning is structurally isomorphic to mathematical reasoning — premise identification, logical chaining, exception handling, structured argumentation toward a conclusion. A model that learned rigorous derivation transfers that structure to legal analysis rather than learning legal templates from scratch. + +**Training format:** + +``` +### Instruction: +{instruction} + +### Response: +{output} +``` + +**Stage 2 hyperparameters:** + +| Parameter | Value | +|---|---| +| Epochs | 1 | +| Effective batch size | 8 | +| Learning rate | 5e-6 (lower than Stage 1 to preserve backbone) | +| Gradient checkpointing | Enabled | +| Precision | bf16 | + +## Model Details + +| Attribute | Value | +|---|---| +| **Architecture** | Qwen3 (causal LM, RoPE, GQA) | +| **Parameters** | 0.6B | +| **Base model** | [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) | +| **Teacher model** | [Qwen/Qwen3-30B-A3B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507) | +| **Compression ratio** | 50x | +| **Stage 1 data** | 6,122 STEM CoT samples (12 datasets) | +| **Stage 2 data** | [Alignment-Lab-AI/Lawyer-Instruct](https://huggingface.co/datasets/Alignment-Lab-AI/Lawyer-Instruct) | +| **Context length** | 1024 tokens (training) | +| **License** | Apache 2.0 | +| **Developer** | Reaperdoesntrun / [Convergent Intelligence LLC](https://convergentintel.com): Research Division | + +## Usage + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model_id = "reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT" + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32, + device_map="auto", +) + +# Legal instruction-following +prompt = """### Instruction: +What is the difference between a felony and a misdemeanor? + +### Response: +""" + +# STEM derivation (Stage 1 format still works) +prompt_stem = """Solve the following problem carefully and show a rigorous derivation. + +Problem: +Compute the determinant of the matrix [[1, 2], [3, 4]]. + +Proof: +""" + +inputs = tokenizer(prompt, return_tensors="pt").to(model.device) +with torch.no_grad(): + outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +### GGUF + +Quantized versions at [reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF). + +## Prompt Formats + +**STEM derivation (Stage 1):** + +``` +Solve the following problem carefully and show a rigorous derivation. + +Problem: +[Your problem] + +Proof: +``` + +**Instruction-following (Stage 2):** + +``` +### Instruction: +[Your question] + +### Response: +``` + +## Intended Uses + +**Good for:** Ultra-lightweight reasoning on mobile/edge/IoT, legal and STEM instruction-following, educational tutoring, embedded inference, component in multi-model pipelines, anywhere you need reasoning in under 500MB. + +**Not for:** Formal proof verification, actual legal counsel, safety-critical analysis, complex multi-step proofs (>8 steps), or long-context tasks beyond 1024 tokens. + +## Limitations + +0.6B is a hard capacity constraint. The model trades depth for deployability. It will make reasoning errors that a larger model would not. Multi-step derivations beyond ~8 steps degrade. Legal reasoning covers general concepts but lacks the nuance of larger models. Performance is weakest on underrepresented domains (molecular biology, physiology). Always verify outputs. + + +## Mathematical Foundations: Discrepancy Calculus (DISC) + +This model is part of a distillation chain built on Discrepancy Calculus — a measure-theoretic framework where the teacher's output distribution is decomposed via the Mesh Fundamental Identity into smooth (AC), jump, and Cantor components. The discrepancy operator $Df(x) = \lim_{\varepsilon \downarrow 0} \frac{1}{\varepsilon} \int_x^{x+\varepsilon} \frac{|f(t) - f(x)|}{|t - x|} dt$ quantifies local structural mismatch that standard KL divergence averages away. + +Full theory: *"On the Formal Analysis of Discrepancy Calculus"* (Colca, 2026; Convergent Intelligence LLC: Research Division). Full methodology: [Structure Over Scale (DOI: 10.57967/hf/8165)](https://doi.org/10.57967/hf/8165). + +## Related Models + +| Model | Description | +|---|---| +| [Qwen3-0.6B-STEM-Proof-Distilled-Thinking](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-STEM-Proof-Distilled-Thinking) | Stage 1 only — pure STEM backbone | +| [Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF) | This model quantized for edge deployment | +| [Qwen3-1.7B-STEM-Proof-Distilled](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-STEM-Proof-Distilled) | Larger 1.7B variant (Instruct teacher) | +| [Qwen3-1.7B-Distilled-30B-A3B-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFT) | Larger 1.7B variant + legal SFT | + +## Citation + +```bibtex +@misc{colca2026thinking06bsft, + title={Two-Stage Reasoning Transfer at 0.6B: Thinking Teacher Distillation + Legal SFT}, + year={2026}, + publisher={HuggingFace}, + url={https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT}, + note={Convergent Intelligence LLC: Research Division} +} +``` + +--- + +*Convergent Intelligence LLC: Research Division* +*"Where classical analysis fails to see, we begin."* + +--- + +## Convergent Intelligence Portfolio + +*Part of the [Qwen3 0.6B Distillation Series](https://huggingface.co/reaperdoesntknow) by [Convergent Intelligence LLC: Research Division](https://huggingface.co/reaperdoesntknow)* + + +# +## Mathematical Foundations: Discrepancy Calculus (DISC) + +This model is part of a distillation chain built on Discrepancy Calculus — a measure-theoretic framework where the teacher's output distribution is decomposed via the Mesh Fundamental Identity into smooth (AC), jump, and Cantor components. The discrepancy operator $Df(x) = \lim_{\varepsilon \downarrow 0} \frac{1}{\varepsilon} \int_x^{x+\varepsilon} \frac{|f(t) - f(x)|}{|t - x|} dt$ quantifies local structural mismatch that standard KL divergence averages away. + +Full theory: *"On the Formal Analysis of Discrepancy Calculus"* (Colca, 2026; Convergent Intelligence LLC: Research Division). Full methodology: [Structure Over Scale (DOI: 10.57967/hf/8165)](https://doi.org/10.57967/hf/8165). + +## Related Models + +| Model | Downloads | Format | +|-------|-----------|--------| +| [Qwen3-0.6B-Distilled-30B-A3B](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B) | 36 | HF | +| [Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF) | 203 | GGUF | + +### Top Models from Our Lab + +| Model | Downloads | +|-------|-----------| +| [Qwen3-1.7B-Thinking-Distil](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Thinking-Distil) | 501 | +| [LFM2.5-1.2B-Distilled-SFT](https://huggingface.co/reaperdoesntknow/LFM2.5-1.2B-Distilled-SFT) | 342 | +| [Qwen3-1.7B-Coder-Distilled-SFT](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT) | 302 | +| [Qwen3-1.7B-Coder-Distilled-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT-GGUF) | 194 | +| [Qwen3-1.7B-Distilled-30B-A3B-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFT-GGUF) | 175 | + +**Total Portfolio: 41 models | 2,781 total downloads** + + +*Last updated: 2026-03-28 12:56 UTC* + + + +## DistilQwen Collection + +This model is part of the **[DistilQwen](https://huggingface.co/collections/reaperdoesntknow/distilqwen-69bf40ec669117e3f069ef1c)** proof-weighted distillation series. +Collection: **9 models** | **2,788 downloads** + +### Teacher Variant Comparison + +| Teacher | Student Size | Strength | Models | +|---------|-------------|----------|--------| +| Qwen3-30B-A3B (Instruct) | 1.7B | Instruction following, structured output, legal reasoning | 3 (833 DL) | +| Qwen3-30B-A3B (Thinking) | 0.6B | Extended deliberation, higher-entropy distributions, proof derivation | 3 (779 DL) **← this model** | +| Qwen3-30B-A3B (Coder) | 1.7B | Structured decomposition, STEM derivation, logical inference | 2 (825 DL) | + +### Methodology + +**The only BF16 collection in the portfolio.** While the broader Convergent Intelligence catalog (43 models, 12,000+ downloads) was trained on CPU at FP32 for $24 total compute, the DistilQwen series was trained on H100 at BF16 with a 30B-parameter teacher. Same methodology, premium hardware. This is what happens when you give the pipeline real compute. + +All models use proof-weighted knowledge distillation: 55% cross-entropy with decaying proof weights (2.5× → 1.5×), 45% KL divergence at T=2.0. The proof weight amplifies loss on reasoning-critical tokens, forcing the student to allocate capacity to structural understanding rather than surface-level pattern matching. + +Full methodology: [Structure Over Scale (DOI: 10.57967/hf/8165)](https://doi.org/10.57967/hf/8165) + +### Related in this series + +- [Qwen3-0.6B-Distilled-30B-A3B](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B) (236 downloads) +- [Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF](https://huggingface.co/reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF) (316 downloads) + + + + diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- 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' }} + {%- 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' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..4c78d0f --- /dev/null +++ b/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "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" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.0.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..c33fb76 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.0.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..d11bee4 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1d2b15ffb4239c2d83a24ca59e35b8cb427a03dcdc3c667bba985e64907b258 +size 1503300328 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..7d75d3b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,29 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}