| .. |
|
LLaMA.py
|
5a79863df3
Increase the sequence length, decrease batch size
|
2 lat temu |
|
LLaMA_8bit.py
|
bd8aac8fa4
Add LLaMA 8-bit support
|
2 lat temu |
|
RWKV.py
|
ff9f649c0c
Remove some unused imports
|
2 lat temu |
|
chat.py
|
1a05860ca3
Ensure proper no-streaming with generation_attempts > 1
|
2 lat temu |
|
deepspeed_parameters.py
|
f38c9bf428
Fix deepspeed (oops)
|
3 lat temu |
|
extensions.py
|
91f5852245
Move bot_picture.py inside the extension
|
2 lat temu |
|
html_generator.py
|
43b6ab8673
Store thumbnails as files instead of base64 strings
|
2 lat temu |
|
models.py
|
bd8aac8fa4
Add LLaMA 8-bit support
|
2 lat temu |
|
shared.py
|
ed8b35efd2
Add --pin-weight parameter for FlexGen
|
2 lat temu |
|
stopping_criteria.py
|
7224343a70
Improve the imports
|
2 lat temu |
|
text_generation.py
|
c93f1fa99b
Count the tokens more conservatively
|
2 lat temu |
|
ui.py
|
2bff646130
Stop chat from flashing dark when processing
|
2 lat temu |
oobabooga
bd8aac8fa4
Add LLaMA 8-bit support