Hugging Face's logo

rawsh
/
q1-3B-PRIME

Text Generation
Safetensors
English
qwen2
conversational
Model card Files Community
rawsh commited on
Commit
fe38048
·
verified ·
1 Parent(s): c4134b3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -20,8 +20,8 @@ Trained using SmallThinker-3B-Preview as a base model (Qwen2.5-3B-Instruct full
20
  | Model | AIME24 | AMC23 | MATH-500 |
21
  |---------|--------|-------|-------|
22
  | Qwen2.5-3B-Instruct | 6.67 | 45 | - |
23
- | **q1-3B-PRIME** | **26.667** | **67.5** | 64.8 |
24
  | SmallThinker-3B-Preview| 16.667 | 57.5 | - |
 
25
  | Eurus-7B-PRIME | **26.667** | 57.8 | **79.2** |
26
  | GPT-4o | 9.3 | 45.8 | 76.4 |
27
 
 
20
  | Model | AIME24 | AMC23 | MATH-500 |
21
  |---------|--------|-------|-------|
22
  | Qwen2.5-3B-Instruct | 6.67 | 45 | - |
 
23
  | SmallThinker-3B-Preview| 16.667 | 57.5 | - |
24
+ | **q1-3B-PRIME** | **26.667** | **67.5** | 64.8 |
25
  | Eurus-7B-PRIME | **26.667** | 57.8 | **79.2** |
26
  | GPT-4o | 9.3 | 45.8 | 76.4 |
27