TheBloke
/

Mistral-7B-Instruct-v0.1-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Resources

View closed (1)

No NVIDIA in _lazy_init

#9 opened 5 months ago by

AttributeError, When using Specific GPU

#8 opened 6 months ago by

Out of memory

#7 opened 6 months ago by

Multilingual Support

#6 opened 6 months ago by

Cuda error for MAX_TOTAL_TOKENS = 8192

#5 opened 7 months ago by

CUDA extension not installed.

#4 opened 7 months ago by

Mistral isn't supported yet

#3 opened 7 months ago by

Exllama

#1 opened 7 months ago by