dufluk

leflak's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in stepfun-ai/Step-3.5-Flash 3 months ago

Hope to see a 4bits AWQ version

👍➕ 10

#25 opened 3 months ago by

leflak

New activity in microsoft/Phi-4-mini-instruct about 1 year ago

Different number of attention heads, makes rotary_ndims vs rope scaling factors wrong?

🤯👀 11

14

#1 opened about 1 year ago by

bartowski

Different number of attention heads, makes rotary_ndims vs rope scaling factors wrong?

🤯👀 11

14

#1 opened about 1 year ago by

bartowski