初始化项目，由ModelHub XC社区提供模型

Model: princeton-nlp/Sheared-LLaMA-2.7B
Source: Original Platform

.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

README.md

@@ -0,0 +1,62 @@
+---
+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-2.7B 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/togethercomputeub.com/togethercomputer/RedPajama-Data). We use 0.4B tokens for pruning and 50B tokens for continued pre-training the pruned model. This model can be loaded into huggingface via
+
+```
+model = AutoModelForCausalLM.from_pretrained("princeton-nlp/Sheared-LLaMA-2.7B")
+```
+
+- 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}
+}
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "princeton-nlp/Sheared-LLaMA-2.7B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 20,
+  "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
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

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"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee766e6759aa2cdd4d3749b25d37b38614c95bfa9cada724a1ba76b04117a9df
+size 9949092725

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fde8a274acfc664a1e726dfd001ce43d86909629f666fd14544fe4d36f4b6d
+size 857268225

pytorch_model.bin.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:166203b1abe5511370379afe798377fc694f30065e49dba2c563c453a2a63d22
+size 26788

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd04f0eadf90287bd26e1a183ac487d8a141b09b06aecb7725bbdd343640f2e
+size 1842767

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}