commit eb47ccee3ec704c2247321721ca95de24d8102e8 Author: ModelHub XC Date: Thu Apr 23 09:15:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/Sparse-Llama-3.1-8B-ultrachat_200k-2of4 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..762cc6a --- /dev/null +++ b/README.md @@ -0,0 +1,60 @@ +--- +tags: +- vllm +- sparsity +pipeline_tag: text-generation +license: llama3.1 +base_model: neuralmagic/Sparse-Llama-3.1-8B-2of4 +datasets: +- HuggingFaceH4/ultrachat_200k +language: +- en +--- + +# Sparse-Llama-3.1-8B-ultrachat_200k-2of4 + +## Model Overview +- **Model Architecture:** Llama-3.1-8B + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Sparsity:** 2:4 +- **Release Date:** 11/21/2024 +- **Version:** 1.0 +- **License(s):** [llama3.1](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B/blob/main/LICENSE) +- **Model Developers:** Neural Magic + +This is a multi-turn conversational AI model obtained by fine-tuning the 2:4 sparse [Sparse-Llama-3.1-8B-2of4](https://huggingface.co/neuralmagic/Sparse-Llama-3.1-8B-2of4) on the [ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) dataset. +On the [AlpacaEval](https://github.com/tatsu-lab/alpaca_eval) benchmark (version 1), it achieves a score of 61.1, compared to 62.0 for the fine-tuned dense model [Llama-3.1-8B-ultrachat_200k](https://huggingface.co/neuralmagic/Llama-3.1-8B-ultrachat_200k) — demonstrating a **98.5% accuracy recovery**. + + +### Model Optimizations + +This inherits the optimizations from its parent, [Sparse-Llama-3.1-8B-2of4](https://huggingface.co/neuralmagic/Sparse-Llama-3.1-8B-2of4). +Namely, all linear operators within transformer blocks were pruned to the 2:4 sparsity pattern: in each group of four weights, two are retained while two are pruned. + + +## Deployment with vLLM + +This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend. vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. + + +## Evaluation + +This model was evaluated on Neural Magic's fork of [AlpacaEval](https://github.com/neuralmagic/alpaca_eval) benchmark. +We adopt the same setup as in [Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment](https://arxiv.org/abs/2405.03594), using version 1 of the benchmark and [Llama-2-70b-chat](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) as the annotator. + +### Accuracy +#### AlpacaEval Benchmark + + + + + + + + + + + +
MetricLlama-3.1-8B-ultrachat_200kSparse-Llama-3.1-8B-ultrachat_200k-2of4
Win rate62.061.1
\ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..dd64a1e --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dccbb02eb4087b834e9a091352b2fb0c3c817dfd24302897d1cd6837ae96a714 +size 1161 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..134c996 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.45.0.dev0" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..8590b04 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb6303dbf401c3a1ec0175690f8647909f6dd5bfd7f36f0c3feed16b9a1daab9 +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..b251a24 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bef2096615122c2a062eaf4a1a407e9760731c6ad14d329a69a606c136c341d4 +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..722a943 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c8d7ca5caceae2e9bcda1f70a6ec6bda4f3a9b4ece738c63a5ea88220fff061 +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..dbbc60e --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9641f6140154bd2dbff35d7649a1f2d9a71cdd0da6c947c83a863be95ca4b4a +size 1168138808 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..a054aad --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b +size 23950 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..b43be96 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..66cd9d7 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4 +size 9085657 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..c1308f3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d82fa0a9ef05b7e9517fb59e0b68c74a742688f22a45e32544f0793fd8fd112a +size 55378