Skip to main content
accuracy-maker
Log in
Sign up
Gao Haitao
accuracy-maker
UNSW
Profile
Reports
LLama3.2-1B Posting Training By GRPO from DeepSeek
Model link: https://huggingface.co/accuracy-maker/Llama-3.2-1B-GRPO-gsm8k Wandb link: https://wandb.ai/accuracy-maker/Llama3.2-1B-GRPO?nw=nwuseraccuracymaker
129 views
Last edit 5 months ago
Activity
Mon
Wed
Fri
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Runs
1-2
of 2
Name
Project
State
Created
Llama-3.2-1B-GRPO-gsm8k-2
Llama3.2-1B-GRPO
Crashed
6 months ago
Llama-3.2-1B-GRPO-gsm8k
Llama3.2-1B-GRPO
Finished
6 months ago
Loading...
