RichardErkhov
/

LoftQ_-_Mistral-7B-v0.1-4bit-32rank-8bits

8-bit precision

Model card Files Files and versions Community

LoftQ_-_Mistral-7B-v0.1-4bit-32rank-8bits / tokenizer.model

Commit History

uploaded model

259f755
verified

RichardErkhov commited on Oct 18, 2024