Hugging Face's logo

Nanbeige
/
Nanbeige4.1-3B

Text Generation
Transformers
Safetensors
English
Chinese
llama
llm
nanbeige
conversational
Eval Results
text-generation-inference
Model card Files
xet
 Community
43

Chain-of-Thought or Chain-of-Mimicry? The Over-SFT problem in Nanbeige 4.1-3B aka "I_Should_X"

#26
by srs6901 - opened
Discussion
srs6901
This comment has been hidden (marked as Resolved)
srs6901
This comment has been hidden (marked as Resolved)
leran1995 changed discussion status to closed

Sign up or log in to comment