commit 1674aa80c5f426a3c30509d249123dd6ef6b0b9e Author: ModelHub XC Date: Thu Apr 23 10:28:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/Sparse-Llama-3.1-8B-gsm8k-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..f64cd44 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +tags: +- vllm +- sparsity +pipeline_tag: text-generation +license: llama3.1 +base_model: neuralmagic/Sparse-Llama-3.1-8B-2of4 +datasets: +- openai/gsm8k +language: +- en +metrics: +- accuracy +--- + +# Sparse-Llama-3.1-8B-gsm8k-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 AI model especialized in grade-school math 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 [GSM8k](https://huggingface.co/datasets/openai/gsm8k) dataset. +It achieves 66.9% 0-shot accuracy on the test set of GSM8k, compared to 66.3% for the fine-tuned dense model [Llama-3.1-8B-gsm8k](https://huggingface.co/neuralmagic/Llama-3.1-8B-gsm8k) — demonstrating over **100% accuracy recovery**. +In constrast, the pretrained [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) achieves 50.7% 5-shot accuracy and the sparse foundational [Sparse-Llama-3.1-8B-2of4](https://huggingface.co/neuralmagic/Sparse-Llama-3.1-8B-2of4) model achieves 56.3% 5-shot accuracy. + + +### 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 the [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). + +### Accuracy +#### GSM8k Benchmark + + + + + + + + + + + + + + + +
MetricLlama-3.1-8B
(5-shot)		Sparse-Llama-3.1-8B-2of4
(5-shot)		Llama-3.1-8B-gsm8k
(0-shot)		Sparse-Llama-3.1-8B-gsm8k-2of4
(0-shot)
Accuracy50.7%56.3%66.3%66.9%
\ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..ee8a553 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f70bc813dd20da9b025b20114e9a8ac79f1b55bcde958d9c611c89547eff45b4 +size 1144 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..db78256 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de42246f80a0b823846cef93fe28caad042e8aa540751b6420af328b9b78f746 +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..50c7c5d --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0725d44c15a2923d453b5d6394430d35c34beae6004a71abf27d17294550a803 +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..f97d987 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65e5e803fdea5bb1a37282080d482a1ce975a2515990506422600641c814b734 +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..acd7a65 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8df205f233579b4915291adc40b8fa1c0fff6db9e2b0b73497df03be4d6e56 +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..04829af --- /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": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|end_of_text|>" +} 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..baa5206 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6344b153070dd9a29e3504d45cb8fccd25d1e2dfca59e897e1936e86d98ac058 +size 50531