ybelkada
/

Mixtral-8x7B-Instruct-v0.1-AWQ

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Resources

View closed (0)

Bad responses for longer context

#6 opened 4 months ago by

latency is slower than standard model, is it normal?

#5 opened 7 months ago by

LorenzoCevolaniAXA

suggestion: add model card

#4 opened 8 months ago by

Perplexity appears high versus casper hansen version

#3 opened 9 months ago by

speed?

#2 opened 11 months ago by

Please upload pt files aswell since vllm does not support safetensors yet in mixtral

#1 opened 11 months ago by