Hugging Face's logo

emotibot-inc
/
Zhuzhi-6B

Feature Extraction
Transformers
PyTorch
chatglm
custom_code
Model card Files Community
Yongning commited on
Commit
c2e9e9a
·
1 Parent(s): cbb7e27

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -32
README.md CHANGED
@@ -20,45 +20,45 @@
20
  | Model 5-shot | STEM | Humanities | Social Science | Other | China-specific | Average |
21
  | --- | --- | --- | --- | --- | --- | --- |
22
  | Multilingual-oriented | | | | | | |
23
- | https://openai.com/gpt4 | 65.23 | 72.11 | 72.06 | 74.79 | 66.12 | 70.95 |
24
- | https://openai.com/chatgpt | 47.81 | 55.68 | 56.50 | 62.66 | 50.69 | 55.51 |
25
- | https://huggingface.co/tiiuae/falcon-40b | 33.33 | 43.46 | 44.28 | 44.75 | 39.46 | 41.45 |
26
- | https://github.com/facebookresearch/llama | 34.47 | 40.24 | 41.55 | 42.88 | 37.00 | 39.80 |
27
- | https://github.com/bigscience-workshop/xmtf | 30.56 | 39.10 | 38.59 | 40.32 | 37.15 | 37.04 |
28
- | https://github.com/mbzuai-nlp/bactrian-x | 27.52 | 32.47 | 32.27 | 35.77 | 31.56 | 31.88 |
29
  | Chinese-oriented | | | | | | |
30
- | Zhuzhi-6B | 40.30 | 48.08 | 46.72 | 47.41 | 45.51 | 45.60 |
31
- | Zhuhai-13B | 42.39 | 61.57 | 60.48 | 58.57 | 55.68 | 55.74 |
32
- | https://github.com/baichuan-inc/Baichuan-13B | 42.38 | 61.61 | 60.44 | 59.26 | 56.62 | 55.82 |
33
- | https://huggingface.co/THUDM/chatglm2-6b | 42.55 | 50.98 | 50.99 | 50.80 | 48.37 | 48.80 |
34
- | https://github.com/baichuan-inc/baichuan-7B | 35.25 | 48.07 | 47.88 | 46.61 | 44.14 | 44.43 |
35
- | https://github.com/THUDM/GLM-130B | 32.35 | 39.22 | 39.65 | 38.62 | 37.70 | 37.48 |
36
- | https://github.com/haonan-li/CMMLU/blob/master | 34.96 | 35.45 | 36.31 | 42.14 | 37.89 | 37.16 |
37
- | https://github.com/ymcui/Chinese-LLaMA-Alpaca | 27.12 | 33.18 | 34.87 | 35.10 | 32.97 | 32.63 |
38
- | https://github.com/OpenLMLab/MOSS | 27.23 | 30.41 | 28.84 | 32.56 | 28.68 | 29.57 |
39
- | https://github.com/THUDM/GLM | 25.49 | 27.05 | 27.42 | 29.21 | 28.05 | 27.26 |
40
  | Random | 25.00 | 25.00 | 25.00 | 25.00 | 25.00 | 25.00 |
41
 
42
  | Model 0-shot | STEM | Humanities | Social Science | Other | China-specific | Average |
43
  | --- | --- | --- | --- | --- | --- | --- |
44
  | Multilingual-oriented | | | | | | |
45
- | https://openai.com/gpt4 | 63.16 | 69.19 | 70.26 | 73.16 | 63.47 | 68.9 |
46
- | https://openai.com/chatgpt | 44.8 | 53.61 | 54.22 | 59.95 | 49.74 | 53.22 |
47
- | https://github.com/bigscience-workshop/xmtf | 33.03 | 45.74 | 45.74 | 46.25 | 41.58 | 42.8 |
48
- | https://huggingface.co/tiiuae/falcon-40b | 31.11 | 41.3 | 40.87 | 40.61 | 36.05 | 38.5 |
49
- | https://github.com/facebookresearch/llama | 31.09 | 34.45 | 36.05 | 37.94 | 32.89 | 34.88 |
50
- | https://github.com/mbzuai-nlp/bactrian-x | 26.46 | 29.36 | 31.81 | 31.55 | 29.17 | 30.06 |
51
  | Chinese-oriented | | | | | | |
52
- | Zhuzhi-6B | 42.51 | 48.91 | 48.85 | 50.25 | 47.57 | 47.62 |
53
- | Zhuhai-13B | 42.37 | 60.97 | 59.71 | 56.35 | 54.81 | 54.84 |
54
- | https://github.com/baichuan-inc/Baichuan-13B | 42.04 | 60.49 | 59.55 | 56.6 | 55.72 | 54.63 |
55
- | https://huggingface.co/THUDM/chatglm2-6b | 41.28 | 52.85 | 53.37 | 52.24 | 50.58 | 49.95 |
56
- | https://github.com/baichuan-inc/baichuan-7B | 32.79 | 44.43 | 46.78 | 44.79 | 43.11 | 42.33 |
57
- | https://github.com/THUDM/GLM-130B | 32.22 | 42.91 | 44.81 | 42.6 | 41.93 | 40.79 |
58
- | https://github.com/haonan-li/CMMLU/blob/master | 33.72 | 36.53 | 38.07 | 46.94 | 38.32 | 38.51 |
59
- | https://github.com/ymcui/Chinese-LLaMA-Alpaca | 26.76 | 26.57 | 27.42 | 28.33 | 26.73 | 27.34 |
60
- | https://github.com/OpenLMLab/MOSS | 25.68 | 26.35 | 27.21 | 27.92 | 26.7 | 26.88 |
61
- | https://github.com/THUDM/GLM | 25.57 | 25.01 | 26.33 | 25.94 | 25.81 | 25.8 |
62
  | Random | 25 | 25 | 25 | 25 | 25 | 25 |
63
 
64
  # **推理对话**
 
20
  | Model 5-shot | STEM | Humanities | Social Science | Other | China-specific | Average |
21
  | --- | --- | --- | --- | --- | --- | --- |
22
  | Multilingual-oriented | | | | | | |
23
+ | [GPT4](https://openai.com/gpt4) | 65.23 | 72.11 | 72.06 | 74.79 | 66.12 | 70.95 |
24
+ | [ChatGPT](https://openai.com/chatgpt) | 47.81 | 55.68 | 56.50 | 62.66 | 50.69 | 55.51 |
25
+ | [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) | 33.33 | 43.46 | 44.28 | 44.75 | 39.46 | 41.45 |
26
+ | [LLaMA-65B](https://github.com/facebookresearch/llama) | 34.47 | 40.24 | 41.55 | 42.88 | 37.00 | 39.80 |
27
+ | [BLOOMZ-7B](https://github.com/bigscience-workshop/xmtf) | 30.56 | 39.10 | 38.59 | 40.32 | 37.15 | 37.04 |
28
+ | [Bactrian-LLaMA-13B](https://github.com/mbzuai-nlp/bactrian-x) | 27.52 | 32.47 | 32.27 | 35.77 | 31.56 | 31.88 |
29
  | Chinese-oriented | | | | | | |
30
+ | [Zhuzhi-6B](https://github.com/emotibot-inc/Zhuzhi-6B) | 40.30 | 48.08 | 46.72 | 47.41 | 45.51 | 45.60 |
31
+ | [Zhuhai-13B](https://github.com/emotibot-inc/Zhuhai-13B) | 42.39 | 61.57 | 60.48 | 58.57 | 55.68 | 55.74 |
32
+ | [Baichuan-13B](https://github.com/baichuan-inc/Baichuan-13B) | 42.38 | 61.61 | 60.44 | 59.26 | 56.62 | 55.82 |
33
+ | [ChatGLM2-6B](https://huggingface.co/THUDM/chatglm2-6b) | 42.55 | 50.98 | 50.99 | 50.80 | 48.37 | 48.80 |
34
+ | [Baichuan-7B](https://github.com/baichuan-inc/baichuan-7B) | 35.25 | 48.07 | 47.88 | 46.61 | 44.14 | 44.43 |
35
+ | [ChatGLM-6B](https://github.com/THUDM/GLM-130B) | 32.35 | 39.22 | 39.65 | 38.62 | 37.70 | 37.48 |
36
+ | [BatGPT-15B](https://github.com/haonan-li/CMMLU/blob/master) | 34.96 | 35.45 | 36.31 | 42.14 | 37.89 | 37.16 |
37
+ | [Chinese-LLaMA-13B](https://github.com/ymcui/Chinese-LLaMA-Alpaca) | 27.12 | 33.18 | 34.87 | 35.10 | 32.97 | 32.63 |
38
+ | [MOSS-SFT-16B](https://github.com/OpenLMLab/MOSS) | 27.23 | 30.41 | 28.84 | 32.56 | 28.68 | 29.57 |
39
+ | [Chinese-GLM-10B](https://github.com/THUDM/GLM) | 25.49 | 27.05 | 27.42 | 29.21 | 28.05 | 27.26 |
40
  | Random | 25.00 | 25.00 | 25.00 | 25.00 | 25.00 | 25.00 |
41
 
42
  | Model 0-shot | STEM | Humanities | Social Science | Other | China-specific | Average |
43
  | --- | --- | --- | --- | --- | --- | --- |
44
  | Multilingual-oriented | | | | | | |
45
+ | [GPT4](https://openai.com/gpt4) | 63.16 | 69.19 | 70.26 | 73.16 | 63.47 | 68.9 |
46
+ | [ChatGPT](https://openai.com/chatgpt) | 44.8 | 53.61 | 54.22 | 59.95 | 49.74 | 53.22 |
47
+ | [BLOOMZ-7B](https://github.com/bigscience-workshop/xmtf) | 33.03 | 45.74 | 45.74 | 46.25 | 41.58 | 42.8 |
48
+ | [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) | 31.11 | 41.3 | 40.87 | 40.61 | 36.05 | 38.5 |
49
+ | [LLaMA-65B](https://github.com/facebookresearch/llama) | 31.09 | 34.45 | 36.05 | 37.94 | 32.89 | 34.88 |
50
+ | [Bactrian-LLaMA-13B](https://github.com/mbzuai-nlp/bactrian-x) | 26.46 | 29.36 | 31.81 | 31.55 | 29.17 | 30.06 |
51
  | Chinese-oriented | | | | | | |
52
+ | [Zhuzhi-6B](https://github.com/emotibot-inc/Zhuzhi-6B) | 42.51 | 48.91 | 48.85 | 50.25 | 47.57 | 47.62 |
53
+ | [Zhuhai-13B](https://github.com/emotibot-inc/Zhuhai-13B) | 42.37 | 60.97 | 59.71 | 56.35 | 54.81 | 54.84 |
54
+ | [Baichuan-13B](https://github.com/baichuan-inc/Baichuan-13B) | 42.04 | 60.49 | 59.55 | 56.6 | 55.72 | 54.63 |
55
+ | [ChatGLM2-6B](https://huggingface.co/THUDM/chatglm2-6b) | 41.28 | 52.85 | 53.37 | 52.24 | 50.58 | 49.95 |
56
+ | [Baichuan-7B](https://github.com/baichuan-inc/baichuan-7B) | 32.79 | 44.43 | 46.78 | 44.79 | 43.11 | 42.33 |
57
+ | [ChatGLM-6B](https://github.com/THUDM/GLM-130B) | 32.22 | 42.91 | 44.81 | 42.6 | 41.93 | 40.79 |
58
+ | [BatGPT-15B](https://github.com/haonan-li/CMMLU/blob/master) | 33.72 | 36.53 | 38.07 | 46.94 | 38.32 | 38.51 |
59
+ | [Chinese-LLaMA-13B](https://github.com/ymcui/Chinese-LLaMA-Alpaca) | 26.76 | 26.57 | 27.42 | 28.33 | 26.73 | 27.34 |
60
+ | [MOSS-SFT-16B](https://github.com/OpenLMLab/MOSS) | 25.68 | 26.35 | 27.21 | 27.92 | 26.7 | 26.88 |
61
+ | [Chinese-GLM-10B](https://github.com/THUDM/GLM) | 25.57 | 25.01 | 26.33 | 25.94 | 25.81 | 25.8 |
62
  | Random | 25 | 25 | 25 | 25 | 25 | 25 |
63
 
64
  # **推理对话**