commit c37eee594854b259f5af2c1290200072c7ddb0db Author: ModelHub XC Date: Sat Jun 20 17:28:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: dystrio/Qwen2.5-3B-Instruct-sculpt-throughput 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..5d14983 --- /dev/null +++ b/README.md @@ -0,0 +1,150 @@ +--- +license: apache-2.0 +library_name: transformers +pipeline_tag: text-generation +language: + - en +base_model: Qwen/Qwen2.5-3B-Instruct +tags: + - dystrio + - sculpt + - pruned + - compressed + - efficient + - dense + - runtime-agnostic + - no-custom-kernels + - hf-drop-in + - drop-in-replacement + - smaller + - faster + - qwen +datasets: + - wikitext +model-index: + - name: Dystrio Sculpt (Qwen2.5-3B-Instruct Throughput) + results: + - task: + type: text-generation + dataset: + name: WikiText-103 (validation) + type: wikitext + metrics: + - name: perplexity + type: perplexity + value: 22.8847 + - name: ppl_ratio + type: ppl_ratio + value: 1.6342 +--- + +# dystrio/Qwen2.5-3B-Instruct-sculpt-throughput + +> **19% smaller, +16% faster prefill, drop-in replacement. No custom kernels. No runtime changes.** + +Dystrio Sculpt structurally compresses transformer models, producing dense models that load with standard `transformers` — no custom code, no new ops, no deployment friction. + +This is the **Throughput** tier of [Qwen2.5 3B Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct). + +## Quick Start + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model = AutoModelForCausalLM.from_pretrained("dystrio/Qwen2.5-3B-Instruct-sculpt-throughput", torch_dtype="bfloat16", device_map="auto") +tokenizer = AutoTokenizer.from_pretrained("dystrio/Qwen2.5-3B-Instruct-sculpt-throughput") + +inputs = tokenizer("The future of AI inference is", return_tensors="pt").to(model.device) +outputs = model.generate(**inputs, max_new_tokens=100) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +## Benchmark Results + +All tiers compiled from [Qwen2.5 3B Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on A100 80GB, bf16: + +| Model | PPL | PPL Ratio | Weights (GB) | Chat Prefill TPS | RAG TTFT p95 (ms) | Decode TPS | +|-------|-----|-----------|-------------|------------------|-------------------|------------| +| **Baseline** | 14.0033 | 1.0 | 5.748009 | 22079.6 | 75.483 | 59.4 | +| **sculpt-default** | 15.5137 | 1.1079 | 5.220665 | 23360.8 | 73.544 | 59.0 | +| **sculpt-production** | 18.9373 | 1.3523 | 4.956993 | 24367.4 | 69.025 | 59.0 | +| **sculpt-throughput** | 22.8847 | 1.6342 | 4.640587 | 25556.6 | 68.084 | 59.0 | +| **sculpt-experimental** | 31.3266 | 2.2371 | 4.165977 | 26731.9 | 66.499 | 59.5 | + +### Key Metrics (this model) + +| Metric | Value | +|--------|-------| +| **Weights memory** | 4.640587 GB (19% smaller) | +| **PPL ratio** | 1.6342 | +| **Chat prefill TPS** | 25556.6 (+16%) | +| **RAG TTFT p95** | 68.084 ms (-10%) | +| **Decode TPS** | 59.0 (flat) | +| **Parameters** | 2.49B | + +## All Sculpt Tiers + +| Tier | HuggingFace | Size | PPL Ratio | Use Case | +|------|-------------|------|-----------|----------| +| default | [dystrio/Qwen2.5-3B-Instruct-sculpt-default](https://huggingface.co/dystrio/Qwen2.5-3B-Instruct-sculpt-default) | 5.220665 GB | 1.1079 | Zero-regret: quality preserved, smaller footprint | +| production | [dystrio/Qwen2.5-3B-Instruct-sculpt-production](https://huggingface.co/dystrio/Qwen2.5-3B-Instruct-sculpt-production) | 4.956993 GB | 1.3523 | Practical savings with modest quality tradeoff | +| throughput | [dystrio/Qwen2.5-3B-Instruct-sculpt-throughput](https://huggingface.co/dystrio/Qwen2.5-3B-Instruct-sculpt-throughput) 👈 **this model** | 4.640587 GB | 1.6342 | Maximum usable compression for speed/edge | +| experimental | [dystrio/Qwen2.5-3B-Instruct-sculpt-experimental](https://huggingface.co/dystrio/Qwen2.5-3B-Instruct-sculpt-experimental) | 4.165977 GB | 2.2371 | Boundary exploration, maximum structural compression | + +## What is Dystrio Sculpt? + +Dystrio Sculpt compiles transformer models into smaller, faster variants. Output models: + +- Are **dense** (not sparse) — standard architecture, fewer parameters +- Load with **standard HuggingFace Transformers** — no custom code needed +- Require **no custom kernels** and **no runtime changes** +- Work as a one-step compile before deployment +- Stack with quantization (AWQ, GPTQ, GGUF) for compound savings + +## Compatibility + +- ✅ HuggingFace Transformers +- ✅ vLLM +- ✅ TGI (Text Generation Inference) +- ✅ llama.cpp / GGUF conversion +- ✅ AWQ / GPTQ quantization +- ✅ Any framework that loads standard safetensors + +## Benchmark Environment + +- **GPU**: NVIDIA A100-SXM4-80GB +- **dtype**: bf16 +- **Torch**: 2.10.0+cu128 +- **Transformers**: 5.3.0 +- **Deterministic**: True +- Single-GPU, standard HuggingFace Transformers, no custom kernels. + +## Metric Definitions + +- **PPL ratio**: WikiText-103 perplexity relative to baseline. <1.0 = quality improved. +- **Prefill TPS**: Tokens per second during prompt encoding (higher = faster). +- **TTFT p95**: Time to first token at 95th percentile (lower = faster). +- **Decode TPS**: Tokens per second during generation (higher = faster). +- **Weights (GB)**: Model parameter memory (deterministic, runtime-independent). + +## Citation + +```bibtex +@misc{dystrio_sculpt_2026, + title={Dystrio Sculpt: Structural Compilation for Transformer LLMs}, + author={Dystrio}, + year={2026}, + url={https://huggingface.co/dystrio} +} +``` + +## Downstream Benchmarks (lm-eval) + +Evaluated with [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness) on A100-80GB, bf16, zero-shot. + +| Benchmark | Baseline | This Model | Delta | +|-----------|:--------:|:----------:|:-----:| +| ARC-Challenge | 0.4573 | 0.3294 | -0.1279 | +| HellaSwag | 0.5635 | 0.4388 | -0.1247 | +| MMLU | 0.6545 | 0.4838 | -0.1707 | +| TruthfulQA MC2 | 0.5874 | 0.5045 | -0.0829 | diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.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' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..cee2949 --- /dev/null +++ b/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8320, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 70, + "model_type": "qwen2", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.3.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..ba6a62d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.3.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..e4ca4ea --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9477e86666891596c9f6ca8e87bebf1c9018cf40d0473a9a0b3e31cee0f827 +size 4982841800 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..4f6ef7a --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:716ec13e363ec927a345aa1d39bb8ed88a0ce7fadcdef14509b1f2afd64a8bee +size 11421990 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 +}