Downloads · 30 days
17
19% of all-time downloads
Qwen2.5-Math-1.5B-GSM8K-EI
michaelbzhu/Qwen2.5-Math-1.5B-GSM8K-EI
Qwen2.5-Math-1.5B-GSM8K-EI is a text generation model from michaelbzhu. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
performed Expert Iteration (EI) on top of michaelbzhu/Qwen2.5-Math-1.5B-GSM8K-SFT
All-time downloads
90
Public
Parameters
1.5B
3.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- qwen2
- Access
- Public
- Created
- Sep 24, 2025
- Updated
- Sep 24, 2025
- SHA
- 620f56a3
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
performed Expert Iteration (EI) on top of michaelbzhu/Qwen2.5-Math-1.5B-GSM8K-SFT
used the following hyperparameters:
n_ei_steps = 60
d_batch_size = 250
G = 30
micro_batch_size = 16
gradient_accum_steps = 2
lr = 1e-5
got these stats on gsm8k test set
correct format: 1312/1319
correct reward: 878/1319
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- mit
- Created
- Sep 24, 2025
- Updated
- Sep 24, 2025