Hugging Face's logo

rawsh
/
q1-3B-PRIME

Text Generation
Safetensors
English
qwen2
conversational
Model card Files
xet
Community
rawsh commited on
Commit
51f782e
·
verified ·
1 Parent(s): 43e56e4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -8
README.md CHANGED
@@ -16,19 +16,17 @@ Trained using SmallThinker-3B-Preview as a base model (Qwen2.5-3B-Instruct full
16
 
17
  # Benchmark Performance
18
 
19
- Math
20
-
21
  | Model | AIME24 | AMC23 | MATH-500 |
22
  |---------|--------|-------|-------|
23
  | Qwen2.5-3B-Instruct | 6.67 | 45 | - |
24
- | **q1-3B-PRIME** | **26.667** | **67.5** | - |
25
  | SmallThinker-3B-Preview| 16.667 | 57.5 | - |
26
- | GPT-4o | 9.3 | 45.8 | 76.4 |
27
-
28
- Coding
29
 
 
30
  | Model | HumanEval | Leetcode |
31
  |---------|--------|-------|
32
- | Qwen2.5-3B-Instruct | **74.4** | - |
33
  | **q1-3B-PRIME** | 71.95 | **20.55** |
34
- | GPT-4o | 90.2 | - |
 
16
 
17
  # Benchmark Performance
18
 
19
+ ## Math
 
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
+ | GPT-4o | 9.3 | 45.8 | **76.4** |
 
 
26
 
27
+ ## Coding
28
  | Model | HumanEval | Leetcode |
29
  |---------|--------|-------|
30
+ | Qwen2.5-3B-Instruct | 74.4 | - |
31
  | **q1-3B-PRIME** | 71.95 | **20.55** |
32
+ | GPT-4o | 90.2 | - |