commit 8e4a5d29bcb0cc564d2bb52fc47ea8dc06643082 Author: ModelHub XC Date: Sun Apr 26 17:58:51 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/Llama-2-7b-pruned70-retrained 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..c54062e --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: neuralmagic/Llama-2-7b-pruned50-retrained +inference: true +model_type: llama +pipeline_tag: text-generation +datasets: + - cerebras/SlimPajama-627B +tags: +- sparse +--- + +# Llama-2-7b-pruned70-retrained + +This repo contains model files for a [Llama 2 7B](https://huggingface.co/meta-llama/Llama-2-7b-hf) model that has had 50% of the parameters pruned in one-shot with [SparseGPT](https://arxiv.org/abs/2301.00774), then retrained by [Cerebras](https://huggingface.co/cerebras) with 50B tokens from SlimPajama while maintaining sparsity. It was then one-shot pruned to 70% sparsity and trained for another 100B tokens. + +Official model weights from [Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment](https://arxiv.org/abs/2405.03594). + +**Authors**: Neural Magic, Cerebras + +## Usage + +Below we share some code snippets on how to get quickly started with running the model. + +### Sparse Transfer + +By leveraging a pre-sparsified model's structure, you can efficiently fine-tune on new data, leading to reduced hyperparameter tuning, training times, and computational costs. Learn about this process [here](https://neuralmagic.github.io/docs-v2/get-started/transfer). + +### Running the model + +This model has not been fine-tuned for instruction-following but may be run with the transformers library. For accelerated inference with sparsity, deploy with [nm-vllm](https://github.com/neuralmagic/nm-vllm) or [deepsparse](https://github.com/neuralmagic/deepsparse). + +```python +# pip install transformers accelerate +from transformers import AutoTokenizer, AutoModelForCausalLM + +tokenizer = AutoTokenizer.from_pretrained("neuralmagic/Llama-2-7b-pruned70-retrained") +model = AutoModelForCausalLM.from_pretrained("neuralmagic/Llama-2-7b-pruned70-retrained", device_map="auto") + +input_text = "Write me a poem about Machine Learning." +input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") + +outputs = model.generate(**input_ids) +print(tokenizer.decode(outputs[0])) +``` + +## Evaluation Benchmark Results + +Model evaluation metrics and results. [UPDATE] + +| Benchmark | Metric | Llama-2-7b | Llama-2-7b-pruned70-retrained | +|------------------------------------------------|---------------|-------------|-------------------------------| +| [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot | 46.9% | 36.5% | +| [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot | 78.6% | 74.1% | +| [WinoGrande](https://arxiv.org/abs/1907.10641) | 5-shot | 74.0% | 69.5% | +| [ARC-c](https://arxiv.org/abs/1911.01547) | 25-shot | 53.1% | 45.4% | +| [TruthfulQA](https://arxiv.org/abs/2109.07958) | 5-shot | 38.8% | 36.7% | +| [GSM8K](https://arxiv.org/abs/2110.14168) | 5-shot | 14.5% | 8.0% | +| [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 13.4% | 14.4% | + +## Model Training Details + +[UPDATE] + +## Help + +For further support, and discussions on these models and AI in general, join [Neural Magic's Slack Community](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ) \ No newline at end of file diff --git a/arc_challenge_25shot_bs16_bf16.json b/arc_challenge_25shot_bs16_bf16.json new file mode 100644 index 0000000..0d6f7bd --- /dev/null +++ b/arc_challenge_25shot_bs16_bf16.json @@ -0,0 +1,25 @@ +{ + "results": { + "arc_challenge": { + "acc": 0.431740614334471, + "acc_stderr": 0.014474591427196206, + "acc_norm": 0.4539249146757679, + "acc_norm_stderr": 0.014549221105171864 + } + }, + "versions": { + "arc_challenge": 0 + }, + "config": { + "model": "sparseml", + "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint,dtype=bfloat16", + "num_fewshot": 25, + "batch_size": "16", + "batch_sizes": [], + "device": "cuda:4", + "no_cache": true, + "limit": null, + "bootstrap_iters": 100000, + "description_dict": {} + } +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..6245920 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "neuralmagic/Llama-2-7b-pruned70-retrained", + "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, + "tokenizer_class": "LlamaTokenizerFast", + "torch_dtype": "bfloat16", + "transformers_version": "4.40.0", + "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..9188e67 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.40.0" +} diff --git a/gsm8k_5shot_bs16_bf16.json b/gsm8k_5shot_bs16_bf16.json new file mode 100644 index 0000000..6a68058 --- /dev/null +++ b/gsm8k_5shot_bs16_bf16.json @@ -0,0 +1,23 @@ +{ + "results": { + "gsm8k": { + "acc": 0.07960576194086429, + "acc_stderr": 0.00745592433867626 + } + }, + "versions": { + "gsm8k": 0 + }, + "config": { + "model": "sparseml", + "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint,dtype=bfloat16", + "num_fewshot": 5, + "batch_size": "16", + "batch_sizes": [], + "device": "cuda:6", + "no_cache": true, + "limit": null, + "bootstrap_iters": 100000, + "description_dict": {} + } +} \ No newline at end of file diff --git a/hellaswag_10shot_bs16_bf16.json b/hellaswag_10shot_bs16_bf16.json new file mode 100644 index 0000000..3f39f4d --- /dev/null +++ b/hellaswag_10shot_bs16_bf16.json @@ -0,0 +1,25 @@ +{ + "results": { + "hellaswag": { + "acc": 0.5493925512846046, + "acc_stderr": 0.004965375341643134, + "acc_norm": 0.7405895239992033, + "acc_norm_stderr": 0.004374153847826759 + } + }, + "versions": { + "hellaswag": 0 + }, + "config": { + "model": "sparseml", + "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint,dtype=bfloat16", + "num_fewshot": 10, + "batch_size": "16", + "batch_sizes": [], + "device": "cuda:2", + "no_cache": true, + "limit": null, + "bootstrap_iters": 100000, + "description_dict": {} + } +} \ No newline at end of file diff --git a/humaneval_fp16.json b/humaneval_fp16.json new file mode 100644 index 0000000..f7339b0 --- /dev/null +++ b/humaneval_fp16.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e58b4257cba27b3176bfa1789bc72526d9d6faff315377073a2cb5b99c51e1 +size 1366 diff --git a/mmlu_5shot_bs4_bf16.json b/mmlu_5shot_bs4_bf16.json new file mode 100644 index 0000000..96a0b1d --- /dev/null +++ b/mmlu_5shot_bs4_bf16.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2929427f3957584b28353ae43428995f13d92f3361b654864e278e4e7cff9539 +size 14303 diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..0c4ebcb --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14de06ce30ff5abb553419bddfbcf4f136bf25acdc6d4b78e81ce52153dd7b0a +size 4938985352 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..d96b40a --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54099b8f1e7e8ad535877bd43c645ff6bb5ea8fecc3b56e5a50235d47e13dbb2 +size 4947390880 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..36c21fc --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:641b79a8e42d777edc8268dd4ce54bfc16d361b47b32294fc22e3c8ca46f0107 +size 3590488816 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..b3d8d7d --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:091fdb60b8ee3713df38fd6f9849c3aa82d7eeeb5f6d224a77139543b1db8652 +size 23950 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "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.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..120fe80 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,41 @@ +{ + "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 + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/truthfulqa_mc_0shot_bs16_bf16.json b/truthfulqa_mc_0shot_bs16_bf16.json new file mode 100644 index 0000000..b7e75e3 --- /dev/null +++ b/truthfulqa_mc_0shot_bs16_bf16.json @@ -0,0 +1,25 @@ +{ + "results": { + "truthfulqa_mc": { + "mc1": 0.2350061199510404, + "mc1_stderr": 0.014843061507731618, + "mc2": 0.3668136165316701, + "mc2_stderr": 0.013583264391841515 + } + }, + "versions": { + "truthfulqa_mc": 1 + }, + "config": { + "model": "sparseml", + "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint,dtype=bfloat16", + "num_fewshot": 0, + "batch_size": "16", + "batch_sizes": [], + "device": "cuda:4", + "no_cache": true, + "limit": null, + "bootstrap_iters": 100000, + "description_dict": {} + } +} \ No newline at end of file diff --git a/winogrande_5shot_bs16_bf16.json b/winogrande_5shot_bs16_bf16.json new file mode 100644 index 0000000..fed752e --- /dev/null +++ b/winogrande_5shot_bs16_bf16.json @@ -0,0 +1,23 @@ +{ + "results": { + "winogrande": { + "acc": 0.6945540647198106, + "acc_stderr": 0.012945038632552029 + } + }, + "versions": { + "winogrande": 0 + }, + "config": { + "model": "sparseml", + "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint,dtype=bfloat16", + "num_fewshot": 5, + "batch_size": "16", + "batch_sizes": [], + "device": "cuda:2", + "no_cache": true, + "limit": null, + "bootstrap_iters": 100000, + "description_dict": {} + } +} \ No newline at end of file