TheBloke
/

Nous-Hermes-Llama-2-7B-GPTQ

Text Generation

synthetic instruction

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Nous-Hermes-Llama-2-7B-GPTQ / quantize_config.json

Commit History

Update for Transformers GPTQ support

f05f8db

TheBloke commited on Aug 20, 2023

Initial GPTQ model commit

4d64c1b

TheBloke commited on Jul 27, 2023