commit f8a07d9ba035b10c286a4ffb8ac241b316a9e5a7 Author: ModelHub XC Date: Sat Jun 20 18:41:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: dystrio/Llama-3.1-8B-Instruct-sculpt-default 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..7fc9ccc --- /dev/null +++ b/README.md @@ -0,0 +1,150 @@ +--- +license: apache-2.0 +library_name: transformers +pipeline_tag: text-generation +language: + - en +base_model: meta-llama/Llama-3.1-8B-Instruct +tags: + - dystrio + - sculpt + - pruned + - compressed + - efficient + - dense + - runtime-agnostic + - no-custom-kernels + - hf-drop-in + - drop-in-replacement + - smaller + - faster + - llama +datasets: + - wikitext +model-index: + - name: Dystrio Sculpt (Llama-3.1-8B-Instruct Default) + results: + - task: + type: text-generation + dataset: + name: WikiText-103 (validation) + type: wikitext + metrics: + - name: perplexity + type: perplexity + value: 14.7778 + - name: ppl_ratio + type: ppl_ratio + value: 1.0641 +--- + +# dystrio/Llama-3.1-8B-Instruct-sculpt-default + +> **10% smaller, quality preserved (1.0641x PPL), 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 **Default** tier of [Llama 3.1 8B Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct). + +## Quick Start + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model = AutoModelForCausalLM.from_pretrained("dystrio/Llama-3.1-8B-Instruct-sculpt-default", torch_dtype="bfloat16", device_map="auto") +tokenizer = AutoTokenizer.from_pretrained("dystrio/Llama-3.1-8B-Instruct-sculpt-default") + +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 [Llama 3.1 8B Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on A100 80GB, bf16: + +| Model | PPL | PPL Ratio | Weights (GB) | Chat Prefill TPS | RAG TTFT p95 (ms) | Decode TPS | +|-------|-----|-----------|-------------|------------------|-------------------|------------| +| **Baseline** | 13.8879 | 1.0 | 14.957527 | 10570.4 | 126.745 | 66.8 | +| **sculpt-default** | 14.7778 | 1.0641 | 13.457527 | 11418.6 | 116.957 | 65.5 | +| **sculpt-production** | 21.9236 | 1.5786 | 11.863777 | 12760.5 | 112.529 | 66.7 | +| **sculpt-throughput** | 27.7463 | 1.9979 | 11.020027 | 13408.6 | 104.086 | 67.5 | +| **sculpt-experimental** | 29.3853 | 2.1159 | 10.832527 | 13483.3 | 103.432 | 67.4 | + +### Key Metrics (this model) + +| Metric | Value | +|--------|-------| +| **Weights memory** | 13.457527 GB (10% smaller) | +| **PPL ratio** | 1.0641 | +| **Chat prefill TPS** | 11418.6 (+8%) | +| **RAG TTFT p95** | 116.957 ms (-8%) | +| **Decode TPS** | 65.5 (flat) | +| **Parameters** | 7.22B | + +## All Sculpt Tiers + +| Tier | HuggingFace | Size | PPL Ratio | Use Case | +|------|-------------|------|-----------|----------| +| default | [dystrio/Llama-3.1-8B-Instruct-sculpt-default](https://huggingface.co/dystrio/Llama-3.1-8B-Instruct-sculpt-default) 👈 **this model** | 13.457527 GB | 1.0641 | Zero-regret: quality preserved, smaller footprint | +| production | [dystrio/Llama-3.1-8B-Instruct-sculpt-production](https://huggingface.co/dystrio/Llama-3.1-8B-Instruct-sculpt-production) | 11.863777 GB | 1.5786 | Practical savings with modest quality tradeoff | +| throughput | [dystrio/Llama-3.1-8B-Instruct-sculpt-throughput](https://huggingface.co/dystrio/Llama-3.1-8B-Instruct-sculpt-throughput) | 11.020027 GB | 1.9979 | Maximum usable compression for speed/edge | +| experimental | [dystrio/Llama-3.1-8B-Instruct-sculpt-experimental](https://huggingface.co/dystrio/Llama-3.1-8B-Instruct-sculpt-experimental) | 10.832527 GB | 2.1159 | 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 | 0.5358 | 0.4283 | -0.1075 | +| HellaSwag | 0.5977 | 0.5416 | -0.0561 | +| MMLU | 0.6844 | 0.5590 | -0.1254 | +| TruthfulQA MC2 | 0.5456 | 0.4824 | -0.0632 | diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..33089ac --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,109 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..e97a26e --- /dev/null +++ b/config.json @@ -0,0 +1,40 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": null, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": false, + "transformers_version": "5.3.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..4663114 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "5.3.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..32e0c35 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:194b3be05822ec65d44921b6b3884d000d5629ec397130324108458e62be3c37 +size 14449943840 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..bdacd85 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13574c77ca1d572525cfa7caac46cee99309100524dad568a7ef85ae383df39f +size 17210018 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b0c7368 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "TokenizersBackend" +}