opter

opter's activity

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

New activity in Qwen/Qwen3-235B-A22B-Instruct-2507 7 months ago

W8A8 Quantization leads to wrong token

👀 1

#31 opened 7 months ago by

opter

New activity in unsloth/gpt-oss-20b-BF16 7 months ago

You give the wrong transpose format of model linear weights

#3 opened 7 months ago by

opter

New activity in deepseek-ai/DeepSeek-R1-0528 9 months ago

int4 quantization destorys function_call accuracy

#99 opened 9 months ago by

opter

int4 quantization destorys function_call accuracy

#99 opened 9 months ago by

opter