commit a26a4e90f972c704aedd447fe2b9405da28b3da0 Author: ModelHub XC Date: Mon Aug 10 06:23:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/SparseLlama-2-7b-evolcodealpaca-pruned_50.2of4 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..f23bd48 --- /dev/null +++ b/README.md @@ -0,0 +1,42 @@ +--- +datasets: +- theblackcat102/evol-codealpaca-v1 +language: +- en +pipeline_tag: text-generation +--- + +# SparseLlama-2-7b-evolcodealpaca-pruned_50.2of4 + +## Model Overview +- **Model Architecture:** Llama-2 + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Pruned:** 50% 2:4 +- **Release Date:** 7/2/2024 +- **Version:** 1.0 +- **Model Developers:** Neural Magic + +Compressed version of [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf) specialized for code-generation. +This model was obtained by fine-tuning the Sparse Foundational model [SparseLlama-2-7b-pruned_50.2of4](https://huggingface.co/nm-testing/SparseLlama-2-7b-pruned_50.2of4) on the [evol-codealpaca-v1](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1) dataset. +[SquareHead](https://arxiv.org/abs/2310.06927) knowledge distillation was used with [Llama-2-7b-evolcodealpaca](https://huggingface.co/neuralmagic/Llama-2-7b-evolcodealpaca) as teacher. +It achieves [HumanEval](https://arxiv.org/abs/2107.03374) pass@1 of 34.58%, whereas the dense [Llama-2-7b-evolcodealpaca](https://huggingface.co/neuralmagic/Llama-2-7b-evolcodealpaca) model achieves 32.03%. + +This model was produced as part if Neural Magic's Sparse Foundational Models initiative, and demostrates the capability of Sparse Foundational Models to transfer to the code-generation domain. + +## Model Optimizations + +This model is derived from the Sparse Foundational model [Sparse-Llama-2-7b-pruned_50.2of4](https://huggingface.co/nm-testing/SparseLlama-2-7b-pruned_50.2of4), which was obtained by applying the [SparseGPT](https://arxiv.org/abs/2301.00774) algorithm to prune [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf) to 50% sparsity with a 2:4 mask. +This optimization reduces the number of parameters by 50%, reducing the disk size and FLOPs by the same level. + +## Evaluation + +This model was evaluated in the [HumanEval](https://arxiv.org/abs/2107.03374) benchmark using the [bigcode-evaluation-harness](https://github.com/bigcode-project/bigcode-evaluation-harness). + +## Accuracy + +| Model | HumanEval pass@1 | Recovery | +| :----- | :--------: | :--------: | +| [Llama-2-7b-evolcodealpaca](https://huggingface.co/neuralmagic/Llama-2-7b-evolcodealpaca) | 32.03% | -- | +| SparseLlama-2-7b-evolcodealpaca-pruned_50.2of4 | 34.58% | 108% | \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..5a103b6 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "/network/eldar/models_to_share/llama2_7b_sp24_v1", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.39.3", + "use_cache": true, + "vocab_size": 32000 +} 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..b8e05e6 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.39.3" +} diff --git a/humaneval_fp16.json b/humaneval_fp16.json new file mode 100644 index 0000000..a85d6d1 --- /dev/null +++ b/humaneval_fp16.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35dcb600471dfee5a7e35983fc4bf7b320532f2af300a3489384bb0adb2b5703 +size 1463 diff --git a/model-00001-of-00006.safetensors b/model-00001-of-00006.safetensors new file mode 100644 index 0000000..486c68d --- /dev/null +++ b/model-00001-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40215e2bd88a070d01e1dcb9067829a1eab1303dde34cc686ba9f726b0f1cceb +size 4840396416 diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors new file mode 100644 index 0000000..0a5b63d --- /dev/null +++ b/model-00002-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8483b404434a5e75497210022fb9c0953fa49ecbc37d07d340c366fd68d0fec +size 4857206856 diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors new file mode 100644 index 0000000..037f11a --- /dev/null +++ b/model-00003-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88e5e230923032efbe14729cd74cec8723126d6d365790cdf98f34259c964a5f +size 4857206904 diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors new file mode 100644 index 0000000..9dd2aa7 --- /dev/null +++ b/model-00004-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f941d3d16ab570ffb8322e8f4501e170779b46f95ae9f21dbea0ab70985b4ae +size 4857206904 diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors new file mode 100644 index 0000000..c5a1870 --- /dev/null +++ b/model-00005-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc6e339fb3ed84a08dfd9c1ab648bc6ea7128f60dc49dfe3f85ea6853228c6b0 +size 4857206904 diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors new file mode 100644 index 0000000..025a36a --- /dev/null +++ b/model-00006-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60d903752a2a270a7f8f6d529ccf0b502b2baf38e844d22ae520e3571b7c73e6 +size 2684472112 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..639555d --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f34eda738bf5f033b7b84a54848f705db21cbf4bee3bf4dfdaf00612fa5bd9d0 +size 23950 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..99b68f6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + "", + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..21779d6 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd04f0eadf90287bd26e1a183ac487d8a141b09b06aecb7725bbdd343640f2e +size 1842767 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..657fa82 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,46 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "" + ], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 4096, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +}