| .. |
|
GPTQ_loader.py
|
f3a2e0b8a9
Disable pre_layer when the model type is not llama
|
2 anos atrás |
|
LoRA.py
|
a21e580782
Move an import
|
2 anos atrás |
|
RWKV.py
|
09b0a3aafb
Add repetition_penalty
|
2 anos atrás |
|
callbacks.py
|
b246d17513
Fix `type object is not subscriptable`
|
2 anos atrás |
|
chat.py
|
ae1fe45bc0
One more cache reset
|
2 anos atrás |
|
deepspeed_parameters.py
|
f38c9bf428
Fix deepspeed (oops)
|
3 anos atrás |
|
extensions.py
|
1edfb96778
Fix loading extensions from within the interface
|
2 anos atrás |
|
html_generator.py
|
8ef89730a5
Try to better handle browser image cache
|
2 anos atrás |
|
llamacpp_model.py
|
2c52310642
Add --threads flag for llama.cpp
|
2 anos atrás |
|
models.py
|
4ab679480e
allow quantized model to be loaded from model dir (#760)
|
2 anos atrás |
|
shared.py
|
65d8a24a6d
Show profile pictures in the Character tab
|
2 anos atrás |
|
text_generation.py
|
b0890a7925
Add shared.is_chat() function
|
2 anos atrás |
|
training.py
|
2a267011dc
Use Path.stem for simplicity
|
2 anos atrás |
|
ui.py
|
d30a14087f
Further reorganize the UI
|
2 anos atrás |
oobabooga
f3a2e0b8a9
Disable pre_layer when the model type is not llama