cArlIcon commited on
Commit
ce65074
1 Parent(s): cd8d59d

update LICENSE and README

Browse files
Files changed (2) hide show
  1. LICENSE +2 -2
  2. README.md +19 -100
LICENSE CHANGED
@@ -190,7 +190,7 @@ latest version of the Agreement will be posted by the Licensor through
190
  https://01.ai.
191
 
192
  For any questions related to licensing and copyright, please contact the
193
- Licensor at oss@01.ai.
194
 
195
 
196
  Yi系列模型许可协议
@@ -324,4 +324,4 @@ Yi系列模型按“原样”提供。许可方不对Yi系列模型提供任何
324
  7. 协议更新及联系方式
325
 
326
  许可方有权对协议进行不时更新。许可方将通过https://01.ai公布协议最新版本。有关许
327
- 可和版权的任何问题,请通过oss@01.ai 与许可方联系。
 
190
  https://01.ai.
191
 
192
  For any questions related to licensing and copyright, please contact the
193
+ Licensor at yi@01.ai.
194
 
195
 
196
  Yi系列模型许可协议
 
324
  7. 协议更新及联系方式
325
 
326
  许可方有权对协议进行不时更新。许可方将通过https://01.ai公布协议最新版本。有关许
327
+ 可和版权的任何问题,请通过yi@01.ai 与许可方联系。
README.md CHANGED
@@ -9,118 +9,36 @@ license_link: LICENSE
9
  Yi
10
  </h1>
11
 
12
- <a href="https://github.com/01-ai/Yi/actions/workflows/ci.yml">
13
- <img src="https://github.com/01-ai/Yi/actions/workflows/ci.yml/badge.svg">
14
- </a>
15
- <a href="https://huggingface.co/01-ai">
16
- <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-01--ai-blue">
17
- </a>
18
- <a href="https://www.modelscope.cn/organization/01ai/">
19
- <img src="https://img.shields.io/badge/ModelScope-01--ai-blue">
20
- </a>
21
- <a href="https://github.com/01-ai/Yi/blob/main/LICENSE">
22
- <img src="https://img.shields.io/github/license/01-ai/yi">
23
- </a>
24
-
25
  </div>
26
 
27
  ## Introduction
28
 
29
- The **Yi** series models are large language models trained from scratch by developers at [01.AI](https://01.ai/). The first public release contains two base models with the parameter size of 6B and 34B. Besides, a specialized version with **200K** context window size is also provided.
30
 
31
  ## News
32
 
33
- - 🎯 **2023/11/05**: The base model of `Yi-6B` and `Yi-34B` (with **200K** context window)
34
 
35
  ## Model Performance
36
 
37
- (FIXME)
38
-
39
- ## Usage
40
-
41
- ### 1. Download the model (optional)
42
-
43
- By default the model weights and tokenizer will be downloaded from [HuggingFace](https://huggingface.co/01-ai) automatically in the next step. You can also download them manually from the following places:
44
-
45
- - ModelScope (FIXME)
46
- - Mirror site (remember to extra the content with `tar`)
47
- - [Yi-6B.tar](https://01-ai.tos-cn-beijing.volces.com/yi/models/Yi-6B.tar)
48
- - [Yi-34B.tar](https://01-ai.tos-cn-beijing.volces.com/yi/models/Yi-34B.tar)
49
-
50
- ### 2. Run with docker
51
-
52
- The recommended approach to try out our models is through docker. We provide the following docker images.
53
-
54
- - `ghcr.io/01-ai/yi:latest`
55
- - `ml-a100-cn-beijing.cr.volces.com/ci/01-ai/yi:latest`
56
-
57
- Note that the `latest` tag always point to the latest code in the `main` branch. To test a stable version, please replace it with a specific [tag](https://github.com/01-ai/Yi/tags).
58
-
59
- #### 2.1 Try out the base model:
60
-
61
- ```bash
62
- docker run -it ghcr.io/01-ai/yi:latest python demo/text_generation.py
63
- ```
64
-
65
- To reuse the downloaded models in the previous step, you can mount them into the container:
66
-
67
- ```bash
68
- docker run -it \
69
- -v /path/to/model:/model \
70
- ghcr.io/01-ai/yi:latest \
71
- python demo/text_generation.py \
72
- --model /model
73
- ```
74
-
75
- For more advanced usage, please refer the [doc](./demo/README.md).
76
-
77
- #### 2.2 Finetuning from the base model:
78
-
79
- ```bash
80
- docker run -it \
81
- -v /path/to/base/model:/base_model \
82
- -v /path/to/save/finetuned/model:/finetuned_model \
83
- ghcr.io/01-ai/yi:latest \
84
- bash finetune/scripts/run_sft_Yi_6b.sh
85
- ```
86
-
87
- Once finished, you can compare the finetuned model and the base model with the following command:
88
-
89
- ```bash
90
- docker run -it \
91
- -v /path/to/save/finetuned/model/:/finetuned_model \
92
- -v /path/to/base/model/:/base_model \
93
- ghcr.io/01-ai/yi:latest \
94
- bash finetune/scripts/run_eval.sh
95
- ```
96
-
97
- For more advanced usage like fine-tuning based on your custom data, please refer the [doc](./finetune/README.md).
98
-
99
- #### 2.3 Quantization
100
-
101
- ```bash
102
- docker run -it \
103
- -v /path/to/base/model:/base_model \
104
- -v /path/to/save/quantization/model:/quantized_model \
105
- ghcr.io/01-ai/yi:latest \
106
- python quantization/gptq/quant_autogptq.py \
107
- --model /base_model \
108
- --output_dir /quantized_model \
109
- --trust_remote_code
110
- ```
111
 
112
- Once finished, you can then evaluate the resulted model as follows:
113
 
114
- ```bash
115
- docker run -it \
116
- -v /path/to/save/quantization/model:/quantized_model \
117
- ghcr.io/01-ai/yi:latest \
118
- python quantization/gptq/eval_quantized_model.py \
119
- --model /quantized_model \
120
- --trust_remote_code
121
- ```
122
 
123
- For more detailed explanation, please read the [doc](./quantization/gptq/README.md)
124
 
125
  ## Disclaimer
126
 
@@ -128,4 +46,5 @@ Although we use data compliance checking algorithms during the training process
128
 
129
  ## License
130
 
131
- The source code in this repo is licensed under the [Apache 2.0 license](./LICENSE). The Yi series model must be adhere to the [Model License Agreement](./MODEL_LICENSE_AGREEMENT.txt).
 
 
9
  Yi
10
  </h1>
11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  </div>
13
 
14
  ## Introduction
15
 
16
+ The **Yi** series models are large language models trained from scratch by developers at [01.AI](https://01.ai/). The first public release contains two base models with the parameter size of 6B and 34B.
17
 
18
  ## News
19
 
20
+ - 🎯 **2023/11/02**: The base model of `Yi-6B` and `Yi-34B`
21
 
22
  ## Model Performance
23
 
24
+ | Model | MMLU | CMMLU | C-Eval | GAOKAO | BBH | Commonsense Reasoning | Reading Comprehension | Math & Code |
25
+ | :------------ | :------: | :------: | :------: | :------: | :------: | :-------------------: | :-------------------: | :---------: |
26
+ | | 5-shot | 5-shot | 5-shot | 0-shot | 3-shot@1 | - | - | - |
27
+ | LLaMA2-34B | 62.6 | - | - | - | 44.1 | 69.9 | 68.0 | 26.0 |
28
+ | LLaMA2-70B | 68.9 | 53.3 | - | 49.8 | 51.2 | 71.9 | 69.4 | 36.8 |
29
+ | Baichuan2-13B | 59.2 | 62.0 | 58.1 | 54.3 | 48.8 | 64.3 | 62.4 | 23.0 |
30
+ | Qwen-14B | 66.3 | 71.0 | 72.1 | 62.5 | 53.4 | 73.3 | 72.5 | 39.8 |
31
+ | Skywork-13B | 62.1 | 61.8 | 60.6 | 68.1 | 41.7 | 72.4 | 61.4 | 24.9 |
32
+ | InternLM-20B | 62.1 | 59.0 | 58.8 | 45.5 | 52.5 | 78.3 | - | 26.0 |
33
+ | Aquila-34B | 67.8 | 71.4 | 63.1 | - | - | - | - | - |
34
+ | Falcon-180B | 70.4 | 58.0 | 57.8 | 59.0 | 54.0 | 77.3 | 68.8 | 34.0 |
35
+ | Yi-6B | 63.2 | 75.5 | 72.0 | 72.2 | 42.8 | 72.3 | 68.7 | 19.8 |
36
+ | **Yi-34B** | **76.3** | **83.7** | **81.4** | **82.8** | **54.3** | **80.1** | **76.4** | **37.1** |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
 
 
38
 
39
+ While benchmarking open-source models, we have observed a disparity between the results generated by our pipeline and those reported in public sources (e.g. OpenCampus). Upon conducting a more in-depth investigation of this difference, we have discovered that various models may employ different prompts, post-processing strategies, and sampling techniques, potentially resulting in significant variations in the outcomes. Our prompt and post-processing strategy remains consistent with the original benchmark, and greedy decoding is employed during evaluation without any post-processing for the generated content. For scores that did not report by original author (including score reported with different setting), we try to get results with our pipeline.
 
 
 
 
 
 
 
40
 
41
+ To extensively evaluate model's capability, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted in a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Due to technical constraints, we did not test Falcon-180 on QuAC and OBQA; the score is derived by averaging the scores on the remaining tasks. Since the scores for these two tasks are generally lower than the average, we believe that Falcon-180B's performance was not underestimated.
42
 
43
  ## Disclaimer
44
 
 
46
 
47
  ## License
48
 
49
+ The Yi series model must be adhere to the [Model License Agreement](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE).
50
+ For any questions related to licensing and copyright, please contact us ([[email protected]](mailto:[email protected])).