Spaces:

huggingchat

/

chat-ui

like 971

Paused

What kind of optimizations are used to run MistralAI/Mixtral-8x7B-Instruct-v0.1 in Hugging Face Chat? Is this the default model in full precision?
Or are there optimizations to reduce memory requirements for running the model? like using float16 or (8-bit & 4-bit) using bitsandbytes
Is Flash Attention 2 is used too ?