Andrew Qian
andrewqian123
AI & ML interests
None yet
Organizations
None yet
andrewqian123's activity
Updated model card on instructions to quantize the model/
#34 opened 2 months ago
by
andrewqian123
Why doesn't the VRAM go down when I quantize to 4 GB (and other issues)
#33 opened 2 months ago
by
andrewqian123
How can I fine-tune using lora? Is there a sample code?
3
#27 opened 3 months ago
by
sinchir0
Making File Compatible With Environments That Do Not Have Flash Attention
#26 opened 3 months ago
by
andrewqian123