Text Generation
Transformers
PyTorch
English
llama
Inference Endpoints
text-generation-inference
hippogriff-30b-chat / config.json

Commit History

Set use_cache to True, otherwise inference performance is poor (#2)
64c10ed

winglian TheBloke commited on

manticore 30b v2, 1.5 epochs
fe118fc

winglian commited on