oobabooga ed8b35efd2 Add --pin-weight parameter for FlexGen 2 年之前
..
LLaMA.py 5a79863df3 Increase the sequence length, decrease batch size 2 年之前
RWKV.py ff9f649c0c Remove some unused imports 2 年之前
chat.py 1a05860ca3 Ensure proper no-streaming with generation_attempts > 1 2 年之前
deepspeed_parameters.py f38c9bf428 Fix deepspeed (oops) 3 年之前
extensions.py 91f5852245 Move bot_picture.py inside the extension 2 年之前
html_generator.py 43b6ab8673 Store thumbnails as files instead of base64 strings 2 年之前
models.py ed8b35efd2 Add --pin-weight parameter for FlexGen 2 年之前
shared.py ed8b35efd2 Add --pin-weight parameter for FlexGen 2 年之前
stopping_criteria.py 7224343a70 Improve the imports 2 年之前
text_generation.py 05e703b4a4 Print the performance information more reliably 2 年之前
ui.py 2bff646130 Stop chat from flashing dark when processing 2 年之前