Hugging Face's logo

PowerInfer
/
SmallThinker-21BA3B-Instruct

Text Generation
Safetensors
English
Model card Files Community
Sorrymaker2024 commited on
Commit
b87c829
·
verified ·
1 Parent(s): 5f20f2f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -12,12 +12,12 @@ without relying on the cloud.
12
  ## Performance
13
  | Model | MMLU | GPQA-diamond | MATH-500 | IFEVAL | LIVEBENCH | HUMANEVAL | Average |
14
  |------------------------------|-------|--------------|----------|--------|-----------|-----------|---------|
15
- | SmallThinker-21BA3B-Instruct | 84.43 | 55.05 | 82.4 | 85.77 | 60.3 | 89.63 | 76.26 |
16
  | Gemma3-12b-it | 78.52 | 34.85 | 82.4 | 74.68 | 44.5 | 82.93 | 66.31 |
17
- | Qwen3-14B | 84.82 | 50 | 84.6 | 85.21 | 59.5 | 88.41 | 75.42 |
18
- | Qwen3-30BA3B | 85.1 | 44.4 | 84.4 | 84.29 | 58.8 | 90.24 | 74.54 |
19
  | Qwen3-8B | 81.79 | 38.89 | 81.6 | 83.92 | 49.5 | 85.9 | 70.26 |
20
- | Phi-4-14B | 84.58 | 55.45 | 80.2 | 63.22 | 42.4 | 87.2 | 68.84 |
21
 
22
  For the MMLU evaluation, we use a 0-shot CoT setting.
23
 
 
12
  ## Performance
13
  | Model | MMLU | GPQA-diamond | MATH-500 | IFEVAL | LIVEBENCH | HUMANEVAL | Average |
14
  |------------------------------|-------|--------------|----------|--------|-----------|-----------|---------|
15
+ | SmallThinker-21BA3B-Instruct | 84.43 | <u>55.05</u> | 82.4 | **85.77** | **60.3** | <u>89.63</u> | **76.26** |
16
  | Gemma3-12b-it | 78.52 | 34.85 | 82.4 | 74.68 | 44.5 | 82.93 | 66.31 |
17
+ | Qwen3-14B | <u>84.82</u> | 50 | **84.6** | <u>85.21</u>| <u>59.5</u> | 88.41 | <u>75.42</u> |
18
+ | Qwen3-30BA3B | **85.1** | 44.4 | <u>84.4</u> | 84.29 | 58.8 | **90.24** | 74.54 |
19
  | Qwen3-8B | 81.79 | 38.89 | 81.6 | 83.92 | 49.5 | 85.9 | 70.26 |
20
+ | Phi-4-14B | 84.58 | **55.45** | 80.2 | 63.22 | 42.4 | 87.2 | 68.84 |
21
 
22
  For the MMLU evaluation, we use a 0-shot CoT setting.
23