OccamRazor
/

pythia-160m-deduped-gptq-4bit

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

pythia-160m-deduped-gptq-4bit

Commit History

Use g instead of b for groupsize

33ed16d

OccamRazor commited on Apr 1, 2023

Add 4-bit quantizations of pythia-160m-deduped

46b0e2c

OccamRazor commited on Mar 29, 2023

initial commit

c80ebb6

OccamRazor commited on Mar 29, 2023