code-llama-70b
#10
by
eramax
- opened
Could you please add 2bit version for https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf that can run in 24G VRAM with good context and ppt.
Could you please add 2bit version for https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf that can run in 24G VRAM with good context and ppt.