This model is shown as quantization of base Qwen/Qwen2.5-Coder-32B, not Qwen/Qwen2.5-Coder-32B-Instruct
#1
by
EmilPi
- opened
Because of this I couldn't find any exllamaV2 quants excluding some unknown guy.
Whoops.. that's on my script, sorry about that :D
Right now is it based on Instruct version?