yi-01-ai commited on
Commit
a24d3f5
1 Parent(s): 1fc65a6

Auto Sync from git://github.com/01-ai/Yi.git/commit/e3e47d27d65641181e2aeb600304181dd2a7230a

Browse files
Files changed (1) hide show
  1. README.md +11 -9
README.md CHANGED
@@ -860,7 +860,7 @@ python quantization/gptq/eval_quantized_model.py \
860
  --trust_remote_code
861
  ```
862
 
863
- <details style="display: inline;"><summary>For a more detailed explanation, see the explanations below. ⬇️</summary> <ul>
864
 
865
  #### GPT-Q quantization
866
 
@@ -885,7 +885,6 @@ python quant_autogptq.py --model /base_model \
885
  --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code
886
  ```
887
 
888
-
889
  ##### Run Quantized Model
890
 
891
  You can run a quantized model using the `eval_quantized_model.py`:
@@ -897,6 +896,7 @@ python eval_quantized_model.py --model /quantized_model --trust_remote_code
897
  </details>
898
 
899
  #### AWQ
 
900
  ```bash
901
  python quantization/awq/quant_autoawq.py \
902
  --model /base_model \
@@ -1017,7 +1017,9 @@ At the same time, we also warmly invite you to join our collaborative effort by
1017
  With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! 🥳
1018
 
1019
  #### Tutorials
 
1020
  ##### English tutorials
 
1021
  | Type | Deliverable | Date | Author |
1022
  |-------------|--------------------------------------------------------|----------------|----------------|
1023
  | Video | [Run dolphin-2.2-yi-34b on IoT Devices](https://www.youtube.com/watch?v=NJ89T5mO25Y) | 2023-11-30 | [Second State](https://github.com/second-state) |
@@ -1025,8 +1027,8 @@ With all these resources at your fingertips, you're ready to start your exciting
1025
  | Video | [Install Yi 34B Locally - Chinese English Bilingual LLM](https://www.youtube.com/watch?v=CVQvj4Wrh4w&t=476s) | 2023-11-05 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
1026
  | Video | [Dolphin Yi 34b - Brand New Foundational Model TESTED](https://www.youtube.com/watch?v=On3Zuv27V3k&t=85s) | 2023-11-27 | [Matthew Berman](https://www.youtube.com/@matthew_berman) |
1027
 
1028
-
1029
  ##### Chinese tutorials
 
1030
  | Type | Deliverable | Date | Author |
1031
  |-------------|--------------------------------------------------------|----------------|----------------|
1032
  | Blog | [实测零一万物Yi-VL多模态语言模型:能准确“识图吃瓜”](https://mp.weixin.qq.com/s/fu4O9XvJ03JhimsEyI-SsQ) | 2024-02-02 | [苏洋](https://github.com/soulteary) |
@@ -1160,8 +1162,8 @@ For detailed capabilities of the Yi series model, see [Yi: Open Foundation Model
1160
 
1161
  ## Benchmarks
1162
 
1163
- - [Chat model performance](#-chat-model-performance)
1164
- - [Base model performance](#-base-model-performance)
1165
 
1166
  ### Chat model performance
1167
 
@@ -1208,19 +1210,19 @@ Yi-9B is almost the best among a range of similar-sized open-source models (incl
1208
 
1209
  - In terms of **overall** ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B.
1210
 
1211
- ![Yi-9B benchmark - overall](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_overall.png?raw=true)
1212
 
1213
  - In terms of **coding** ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B.
1214
 
1215
- ![Yi-9B benchmark - code](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_code.png?raw=true)
1216
 
1217
  - In terms of **math** ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B.
1218
 
1219
- ![Yi-9B benchmark - math](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_math.png?raw=true)
1220
 
1221
  - In terms of **common sense and reasoning** ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B.
1222
 
1223
- ![Yi-9B benchmark - text](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_text.png?raw=true)
1224
 
1225
  <p align="right"> [
1226
  <a href="#top">Back to top ⬆️ </a> ]
 
860
  --trust_remote_code
861
  ```
862
 
863
+ <details style="display: inline;"><summary>For details, see the explanations below. ⬇️</summary> <ul>
864
 
865
  #### GPT-Q quantization
866
 
 
885
  --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code
886
  ```
887
 
 
888
  ##### Run Quantized Model
889
 
890
  You can run a quantized model using the `eval_quantized_model.py`:
 
896
  </details>
897
 
898
  #### AWQ
899
+
900
  ```bash
901
  python quantization/awq/quant_autoawq.py \
902
  --model /base_model \
 
1017
  With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! 🥳
1018
 
1019
  #### Tutorials
1020
+
1021
  ##### English tutorials
1022
+
1023
  | Type | Deliverable | Date | Author |
1024
  |-------------|--------------------------------------------------------|----------------|----------------|
1025
  | Video | [Run dolphin-2.2-yi-34b on IoT Devices](https://www.youtube.com/watch?v=NJ89T5mO25Y) | 2023-11-30 | [Second State](https://github.com/second-state) |
 
1027
  | Video | [Install Yi 34B Locally - Chinese English Bilingual LLM](https://www.youtube.com/watch?v=CVQvj4Wrh4w&t=476s) | 2023-11-05 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
1028
  | Video | [Dolphin Yi 34b - Brand New Foundational Model TESTED](https://www.youtube.com/watch?v=On3Zuv27V3k&t=85s) | 2023-11-27 | [Matthew Berman](https://www.youtube.com/@matthew_berman) |
1029
 
 
1030
  ##### Chinese tutorials
1031
+
1032
  | Type | Deliverable | Date | Author |
1033
  |-------------|--------------------------------------------------------|----------------|----------------|
1034
  | Blog | [实测零一万物Yi-VL多模态语言模型:能准确“识图吃瓜”](https://mp.weixin.qq.com/s/fu4O9XvJ03JhimsEyI-SsQ) | 2024-02-02 | [苏洋](https://github.com/soulteary) |
 
1162
 
1163
  ## Benchmarks
1164
 
1165
+ - [Chat model performance](#chat-model-performance)
1166
+ - [Base model performance](#base-model-performance)
1167
 
1168
  ### Chat model performance
1169
 
 
1210
 
1211
  - In terms of **overall** ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B.
1212
 
1213
+ ![Yi-9B benchmark - overall](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_overall.png?raw=true)
1214
 
1215
  - In terms of **coding** ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B.
1216
 
1217
+ ![Yi-9B benchmark - code](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_code.png?raw=true)
1218
 
1219
  - In terms of **math** ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B.
1220
 
1221
+ ![Yi-9B benchmark - math](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_math.png?raw=true)
1222
 
1223
  - In terms of **common sense and reasoning** ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B.
1224
 
1225
+ ![Yi-9B benchmark - text](https://github.com/01-ai/Yi/blob/main/assets/img/Yi-9B_benchmark_text.png?raw=true)
1226
 
1227
  <p align="right"> [
1228
  <a href="#top">Back to top ⬆️ </a> ]