Downloads · 30 days
32
4% of all-time downloads
q1-3B-PRIME
rawsh/q1-3B-PRIME
q1-3B-PRIME is a text generation model from rawsh. Use it when you need the model to write or continue text.
q1-3B-PRIME, a small reasoning model trained with reinforcement learning.
All-time downloads
861
Public
Parameters
3.4B
217 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors13.6 GB · 100%
At a glance
- Task
- Text Generation
- Model type
- qwen2
- Access
- Public
- Created
- Jan 16, 2025
- Updated
- Jan 20, 2025
- SHA
- 19511ebd
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
q1-3B-PRIME
q1-3B-PRIME, a small reasoning model trained with reinforcement learning.
Trained using SmallThinker-3B-Preview as a base model (Qwen2.5-3B-Instruct full finetuned on QwQ reasoning traces) for a roughly ~22.5% improvement on the test set in 120 training steps. (Note: lots of performance left on the table since PRIME saturates after 300+ steps.)
Benchmark Performance
Math
| Model | AIME24 | AMC23 | MATH-500 |
|---|---|---|---|
| Qwen2.5-3B-Instruct | 6.67 | 45 | - |
| SmallThinker-3B-Preview | 16.667 | 57.5 | - |
| q1-3B-PRIME | 26.667 | 67.5 | 64.8 |
| Eurus-7B-PRIME | 26.667 | 57.8 | 79.2 |
| GPT-4o | 9.3 | 45.8 | 76.4 |
Coding
| Model | HumanEval | Leetcode |
|---|---|---|
| Qwen2.5-3B-Instruct | 74.4 | - |
| q1-3B-PRIME | 71.95 | 20.55 |
| GPT-4o | 90.2 | - |
- Task
- Text Generation
- Type
- qwen2
- Languages
- en
- Created
- Jan 16, 2025
- Updated
- Jan 20, 2025