abc

abcstar's activity

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

New activity in deepseek-ai/DeepSeek-V3.1 3 months ago

why all the scale values of attn out_proj have the none-zero mantissa 0b111010101010010101001111111101 ?

#22 opened 3 months ago by

abcstar