commit d8edba39473bb096b48802a236b651a4efa9b1d2 Author: ModelHub XC Date: Tue May 5 22:44:33 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: princeton-nlp/Sheared-LLaMA-1.3B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21b3632 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm 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 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..b8d5098 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +license: apache-2.0 +--- + +**Paper**: [https://arxiv.org/pdf/2310.06694.pdf](https://arxiv.org/pdf/2310.06694.pdf) +**Code**: https://github.com/princeton-nlp/LLM-Shearing +**Models**: [Sheared-LLaMA-1.3B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B), [Sheared-LLaMA-2.7B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-2.7B) +**Pruned Models without Continued Pre-training**: [Sheared-LLaMA-1.3B-Pruned](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B-Pruned), [Sheared-LLaMA-2.7B-Pruned](https://huggingface.co/princeton-nlp/Sheared-LLaMA-2.7B-Pruned) +**Instruction-tuned Models**: [Sheared-LLaMA-1.3B-ShareGPT](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B-ShareGPT), [Sheared-LLaMA-2.7B-ShareGPT](https://huggingface.co/princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT) + +**License**: Must comply with license of Llama2 since it's a model derived from Llama2. + +--- + +Sheared-LLaMA-1.3B is a model pruned and further pre-trained from [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf). We dynamically load data from different domains in the [RedPajama dataset](https://github.com/togethercomputer/RedPajama-Data) to prune and contune pre-train the model. We use 0.4B tokens for pruning and 50B tokens for continued pre-training the pruned model. This model can be loaded with HuggingFace via + +``` +model = AutoModelForCausalLM.from_pretrained("princeton-nlp/Sheared-LLaMA-1.3B") +``` + +- Smaller-scale +- Same vocabulary as LLaMA1 and LLaMA2 +- Derived with a budget of 50B tokens by utilizing existing strong LLMs + +## Downstream Tasks + +We evaluate on an extensive set of downstream tasks including reasoning, reading comprehension, language modeling and knowledge intensive tasks. Our Sheared-LLaMA models outperform existing large language models. + +| Model | # Pre-training Tokens | Average Performance | +| ------------------- | --------------------- | ------------------- | +| LLaMA2-7B | 2T | 64.6 | + +**1.3B** + +| Model | # Pre-training Tokens | Average Performance | +| ------------------- | --------------------- | ------------------- | +| OPT-1.3B | 300B | 48.2 | +| Pythia-1.4B | 300B | 48.9 | +| **Sheared-LLaMA-1.3B** | **50B** | **51.0** | + +**3B** + +| Model | # Pre-training Tokens | Average Performance | +| ------------------- | --------------------- | ------------------- | +| OPT-2.7B | 300B | 51.4 | +| Pythia-2.8B | 300B | 52.5 | +| INCITE-Base-3B | 800B | 54.7 | +| Open-LLaMA-3B-v1 | 1T | 55.1 | +| Open-LLaMA-3B-v2 | 1T | 55.7 | +| Sheared-LLaMA-2.7B | 50B | 56.7 | + +## Bibtex +``` +@article{xia2023sheared, + title={Sheared llama: Accelerating language model pre-training via structured pruning}, + author={Xia, Mengzhou and Gao, Tianyu and Zeng, Zhiyuan and Chen, Danqi}, + journal={arXiv preprint arXiv:2310.06694}, + year={2023} +} +``` + +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_princeton-nlp__Sheared-LLaMA-1.3B) + +| Metric | Value | +|-----------------------|---------------------------| +| Avg. | 31.47 | +| ARC (25-shot) | 32.85 | +| HellaSwag (10-shot) | 60.91 | +| MMLU (5-shot) | 25.71 | +| TruthfulQA (0-shot) | 37.14 | +| Winogrande (5-shot) | 58.64 | +| GSM8K (5-shot) | 0.45 | +| DROP (3-shot) | 4.56 | diff --git a/config.json b/config.json new file mode 100644 index 0000000..d3b41b3 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "princeton-nlp/Sheared-LLaMA-1.3B", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 5504, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 16, + "num_hidden_layers": 24, + "num_key_value_heads": 16, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.28.1", + "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..1372199 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.28.1" +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..c2815f8 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46bb5014c44a4273f86e9c5f6166c29719ad4ec1bcd935575d9c696dc2505673 +size 5381778489 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..d85ba6c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5c77a6b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9ffc4aede0845ab65324ce5dccb823dca2427f9a0710981e5bc2398d73d8162 +size 1842665 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..400e3de --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +}