Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
Paper • 2410.18252 • Published • 7 •
2
Michael N
mnoukhov
AI & ML interests
Representation learning for functional language
Recent Activity
updated a dataset 2 days ago
mnoukhov/gsm8k-platinum-qwen2.5-0.5b-base-1024samples-buckets published a dataset 2 days ago
mnoukhov/gsm8k-platinum-qwen2.5-0.5b-base-1024samples-buckets updated a dataset 2 days ago
mnoukhov/gsm8k-platinum-qwen2.5-0.5b-base-1024samplesOrganizations
Incompatibility for Ministral between vllm 0.12.0 and hf transformers 5.0.0
1
#4 opened 4 months ago
by mnoukhov
Confusion on Scheduler
👍 1
1
#2 opened about 1 year ago
by 
Gaaaavin
commented a
paper over 1 year ago