TheBloke
/

OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ / quantize_config.json

Commit History

Update for Transformers GPTQ support

14a2b99

TheBloke commited on Aug 20, 2023

Re-done GPTQ, quantised with sequence length 8K

071d962

TheBloke commited on Jul 25, 2023

Initial GPTQ model commit

0d495cf

TheBloke commited on Jul 25, 2023