Shaobai Jiang
shaobaij
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
21 minutes ago
Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
upvoted
a
paper
24 minutes ago
Likelihood-Based Reward Designs for General LLM Reasoning
upvoted
a
paper
34 minutes ago
Learning to Reason in 13 Parameters
Organizations
None yet
Fine tune 120b at 8 H100s getting cuda OOM error
👀
1
6
#117 opened 6 months ago
by
jinxu88
FlashInfer requires sm75+
7
#48 opened 6 months ago
by
hrithiksagar-tih
If I trained a model on mistral already, do I need to start from scratch due to difficulties of fine-tuning?
2
#62 opened over 2 years ago
by
brando
Cant run the model with the most basic code
👍
6
6
#7 opened over 2 years ago
by
masterchop