初始化项目，由ModelHub XC社区提供模型

Model: Data-Juicer/LLaMA2-7B-ZH-Chat-52k
Source: Original Platform

.gitattributes

@@ -0,0 +1,38 @@
+*.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
+pytorch_model-00001-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+frameworks:
+- Pytorch
+license: Apache License 2.0
+tasks:
+- text-generation
+datasets:
+  train:
+    - Data-Juicer/alpaca-cot-zh-refined-by-data-juicer
+tags:
+- data-juicer
+- arxiv:2309.02033
+---
+## News
+ Our first data-centric LLM competition begins! Please visit the competition's official websites, **FT-Data Ranker** ([1B Track](https://tianchi.aliyun.com/competition/entrance/532157), [7B Track](https://tianchi.aliyun.com/competition/entrance/532158)), for more information.
+## Introduction
+This is a reference LLM from [Data-Juicer](https://github.com/alibaba/data-juicer).
+
+The model architecture is LLaMA2-7B and we built it upon the a pre-trained Chinese checkpoint from [FlagAlpha](https://huggingface.co/FlagAlpha/Atom-7B). 
+The model is fine-trained on 52k Chinese chat samples of Data-Juicer's refined [alpaca-CoT data](https://github.com/alibaba/data-juicer/blob/main/configs/data_juicer_recipes/alpaca_cot/README.md#refined-alpaca-cot-dataset-meta-info).
+It beats LLaMA2-7B fine-tuned on 543k Belle samples in GPT-4 evaluation.
+
+For more details, please refer to our [paper](https://arxiv.org/abs/2309.02033).
+
+![exp_llama](https://img.alicdn.com/imgextra/i2/O1CN019WtUPP1uhebnDlPR8_!!6000000006069-2-tps-2530-1005.png)
+
+## 使用
+```python
+
+from modelscope import (
+    AutoModelForCausalLM, AutoTokenizer, GenerationConfig, snapshot_download
+)
+model_dir = 'LLaMA2-7B-ZH-Chat-52k'
+
+tokenizer = AutoTokenizer.from_pretrained(model_dir)
+model = AutoModelForCausalLM.from_pretrained(model_dir).eval()
+
+inputs = tokenizer('How are you?', return_tensors='pt').to(model.device)
+response = model.generate(inputs.input_ids, max_length=128)
+print(tokenizer.decode(response.cpu()[0], skip_special_tokens=True))
+```
+
+## 参考
+If you find our work useful for your research or development, please kindly cite the following [paper](https://arxiv.org/abs/2309.02033).
+```
+@misc{chen2023datajuicer,
+title={Data-Juicer: A One-Stop Data Processing System for Large Language Models},
+author={Daoyuan Chen and Yilun Huang and Zhijian Ma and Hesen Chen and Xuchen Pan and Ce Ge and Dawei Gao and Yuexiang Xie and Zhaoyang Liu and Jinyang Gao and Yaliang Li and Bolin Ding and Jingren Zhou},
+year={2023},
+eprint={2309.02033},
+archivePrefix={arXiv},
+primaryClass={cs.LG}
+}
+```
+
+#### Clone with HTTP
+```bash
+ git clone https://www.modelscope.cn/Data-Juicer/LLaMA2-7B-ZH-Chat-52k.git
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "flagalpha-7b_zh_sft_verb_52000",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 65000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "temperature": 0.3,
+  "top_p": 0.95,
+  "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9282ea25e3c35f5ca7d6947da368987827cb8169e6e840f7caebf446a956f3b5
+size 9969868716

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6bdc26d36880b3c67d03702af2d2e7ccf5fb0eb0b24a8c9d4e3fa695920da9
+size 9982883010

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e9058cdf90c2d03ccde6cba48c42c5638712566710be5a2ece743eab7de19e
+size 8082373577

pytorch_model.bin.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5657461d1c65b228e3d1b181993f28ab6824e26a093f9a280e1d5508bdf048f
+size 26788

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ef61cc08360cd193f9056cb10e26525451fd62759ca714840663257e7bcdd8
+size 1011042

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}