You can deploy this model and start earning money today!

michaelbzhu/
Qwen2.5-Math-1.5B-GSM8K-SFT

Name: Qwen2.5-Math-1.5B-GSM8K-SFT
Availability: InStock

Views

No views yet

sft finetuned on gsm8k dataset

used the format

<think>{thinking tokens}</think> <answer>{final answer}</answer>

got these stats on gsm8k test set after 2 epochs

correct format: 1260/1319
correct reward: 515/1319

michaelbzhu/Qwen2.5-Math-1.5B-GSM8K-SFT