commit 09524b7992b02bea58ea481437356903a3b3a18e Author: ModelHub XC Date: Mon May 18 11:19:02 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: princeton-nlp/Sheared-LLaMA-1.3B-ShareGPT Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..35d9c68 --- /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 + +test/temp0.0_num1.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..4457aee --- /dev/null +++ b/README.md @@ -0,0 +1,34 @@ +--- +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) + + +## Training information +This is the instruction tuned version of [princeton-nlp/Sheared-LLaMA-1.3B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B). We trained the base model on 10,000 instruction-response pairs +sampled from the ShareGPT dataset (first-turns only). We use the following prompt to perform instruction tuning. + +> You are a helpful assistant. Write a response that appropriately completes the request.\n\n### Input:\n{input}\n\n### Response: + +This model can be loaded through transformers.LlamaModelForCausalLM as follows: + +``` +from transformers import LlamaModelForCausalLM +model = LlamaModelForCausalLM.from_pretrained("princeton-nlp/Sheared-LLaMA-1.3B-ShareGPT") +``` + +## Bibtex + +If you find our model useful, consider citing us with: +``` +@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} +} +``` + diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..e41416d --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "[PAD]": 32000 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..6befb22 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "/scratch/gpfs/mengzhou/space2/out/test_round23_mosaicml_version5/llama2_7b_pruning_scaling_doremi_to1.3b_sl4096_finetune_bs1M_fullrun/checkpoint-51200", + "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": "4.28.0", + "use_cache": true, + "vocab_size": 32001 +} 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..07ca234 --- /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": "4.28.0" +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..e34735d --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e92f22d074488600dcc7e174437979ca027c20a578060a45e1573e5660ea4706 +size 5381798337 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..599f3bb --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "[PAD]", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/test/temp0.0_num1.json b/test/temp0.0_num1.json new file mode 100644 index 0000000..51c14aa --- /dev/null +++ b/test/temp0.0_num1.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ac457b8dad0799a59ba96959f5d62068bbb3ad61366012ecb8c5ba7f36fb5e +size 1801445 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..3dbd131 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "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": 512, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..334b89d --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,123 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.0, + "global_step": 158, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.13, + "learning_rate": 4.986836074908616e-05, + "loss": 1.2069, + "step": 10 + }, + { + "epoch": 0.25, + "learning_rate": 4.882355001067892e-05, + "loss": 1.1431, + "step": 20 + }, + { + "epoch": 0.38, + "learning_rate": 4.677782485216644e-05, + "loss": 1.1003, + "step": 30 + }, + { + "epoch": 0.51, + "learning_rate": 4.381713366536311e-05, + "loss": 1.1053, + "step": 40 + }, + { + "epoch": 0.63, + "learning_rate": 4.0065865909481417e-05, + "loss": 1.0894, + "step": 50 + }, + { + "epoch": 0.76, + "learning_rate": 3.568162605525953e-05, + "loss": 1.1011, + "step": 60 + }, + { + "epoch": 0.89, + "learning_rate": 3.084861204504122e-05, + "loss": 1.0828, + "step": 70 + }, + { + "epoch": 1.01, + "learning_rate": 2.5769876463904265e-05, + "loss": 1.0248, + "step": 80 + }, + { + "epoch": 1.14, + "learning_rate": 2.0658795558326743e-05, + "loss": 0.6882, + "step": 90 + }, + { + "epoch": 1.27, + "learning_rate": 1.5730104520100982e-05, + "loss": 0.6468, + "step": 100 + }, + { + "epoch": 1.27, + "eval_loss": 1.0625633001327515, + "eval_runtime": 0.5552, + "eval_samples_per_second": 18.01, + "eval_steps_per_second": 1.801, + "step": 100 + }, + { + "epoch": 1.39, + "learning_rate": 1.1190875675987356e-05, + "loss": 0.6445, + "step": 110 + }, + { + "epoch": 1.52, + "learning_rate": 7.231818622338823e-06, + "loss": 0.6496, + "step": 120 + }, + { + "epoch": 1.65, + "learning_rate": 4.019267817841835e-06, + "loss": 0.6305, + "step": 130 + }, + { + "epoch": 1.77, + "learning_rate": 1.6881942648911076e-06, + "loss": 0.6451, + "step": 140 + }, + { + "epoch": 1.9, + "learning_rate": 3.3653488440851255e-07, + "loss": 0.6417, + "step": 150 + }, + { + "epoch": 2.0, + "step": 158, + "total_flos": 8944339187138560.0, + "train_loss": 0.8824256341668624, + "train_runtime": 246.3648, + "train_samples_per_second": 81.099, + "train_steps_per_second": 0.641 + } + ], + "max_steps": 158, + "num_train_epochs": 2, + "total_flos": 8944339187138560.0, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..57390d7 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1c394feff2b750998dd3075b59737b03e13d0727e87ad86f9ad4be0d65171b0 +size 4027