Commit History

fix max_new_toke_issue
09fa1cc

Lahiru Menikdiwela commited on

fix cuda issiue on new llama added code
793459b

Lahiru Menikdiwela commited on

changes done according to llama model
173b5f1

Lahiru Menikdiwela commited on

add summarization prompts and op format
94ca250

Lahiru Menikdiwela commited on

load model in 4bit and bfloat16 computying type with pipeline op check
638094e

Lahiru Menikdiwela commited on