Shaobai Jiang

shaobaij

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 6 hours ago

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

upvoted a paper about 9 hours ago

Scaling Domain Data Repetition in LLM Pretraining

upvoted a paper about 12 hours ago

MemHarness: Memory Is Reconstructed, Not Replayed

View all activity

Organizations

None yet

New activity in openai/gpt-oss-120b about 1 year ago

Fine tune 120b at 8 H100s getting cuda OOM error

#117 opened about 1 year ago by

FlashInfer requires sm75+

#48 opened about 1 year ago by

hrithiksagar-bgen

New activity in mistralai/Mistral-7B-v0.1 almost 3 years ago

If I trained a model on mistral already, do I need to start from scratch due to difficulties of fine-tuning?

#62 opened almost 3 years ago by

Cant run the model with the most basic code

#7 opened almost 3 years ago by