Text Generation
Transformers
Safetensors
mistral
openchat
C-RLFT
conversational
text-generation-inference
4-bit precision
gptq
TheBloke commited on
Commit
b5504cb
1 Parent(s): fddf4a7

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -7
README.md CHANGED
@@ -587,15 +587,11 @@ All models are evaluated in chat mode (e.g. with the respective conversation tem
587
 
588
  *: Grok results are reported by [X.AI](https://x.ai/).
589
 
590
- <div>
591
- <h3>Massive Multitask Language Understanding in Chinese (CMMLU)</h3>
592
- 5-shot:
593
  </div>
594
 
595
- | Models | STEM | Humanities | SocialSciences | Other | ChinaSpecific | Avg |
596
- |----------|-------|------------|----------------|-------|---------------|-------|
597
- | ChatGPT | 47.81 | 55.68 | 56.5 | 62.66 | 50.69 | 55.51 |
598
- | OpenChat | 38.7 | 45.99 | 48.32 | 50.23 | 43.27 | 45.85 |
599
 
600
  <div>
601
  <h3>Multi-Level Multi-Discipline Chinese Evaluation Suite (CEVAL)</h3>
@@ -606,6 +602,14 @@ All models are evaluated in chat mode (e.g. with the respective conversation tem
606
  | ChatGPT | 54.4 | 52.9 | 61.8 | 50.9 | 53.6 |
607
  | OpenChat | 47.29 | 45.22 | 52.49 | 48.52 | 45.08 |
608
 
 
 
 
 
 
 
 
 
609
 
610
  <div align="center">
611
  <h2> Limitations </h2>
 
587
 
588
  *: Grok results are reported by [X.AI](https://x.ai/).
589
 
590
+ <div align="center">
591
+ <h2> 中文评估结果 / Chinese Evaluations </h2>
 
592
  </div>
593
 
594
+ ⚠️ Note that this model was not explicitly trained in Chinese (only < 0.1% of the data is in Chinese). 请注意本模型没有针对性训练中文(中文数据占比小于0.1%)。
 
 
 
595
 
596
  <div>
597
  <h3>Multi-Level Multi-Discipline Chinese Evaluation Suite (CEVAL)</h3>
 
602
  | ChatGPT | 54.4 | 52.9 | 61.8 | 50.9 | 53.6 |
603
  | OpenChat | 47.29 | 45.22 | 52.49 | 48.52 | 45.08 |
604
 
605
+ <div>
606
+ <h3>Massive Multitask Language Understanding in Chinese (CMMLU, 5-shot)</h3>
607
+ </div>
608
+
609
+ | Models | STEM | Humanities | SocialSciences | Other | ChinaSpecific | Avg |
610
+ |----------|-------|------------|----------------|-------|---------------|-------|
611
+ | ChatGPT | 47.81 | 55.68 | 56.5 | 62.66 | 50.69 | 55.51 |
612
+ | OpenChat | 38.7 | 45.99 | 48.32 | 50.23 | 43.27 | 45.85 |
613
 
614
  <div align="center">
615
  <h2> Limitations </h2>