this is 4 bit quantized?
#3
by
Clausss
- opened
same as title
Yes, uses Qwen2.5-Coder-1.5B-Instruct-q4f16_1-MLC
https://github.com/cfahlgren1/qwen-2.5-code-interpreter/blob/main/app/hooks/useModelLoading.ts
Clausss
changed discussion status to
closed