| .. |
|
GPTQ_loader.py
|
ee4547cd34
Detect "vicuna" as llama model type (#772)
|
2 rokov pred |
|
LoRA.py
|
a21e580782
Move an import
|
2 rokov pred |
|
RWKV.py
|
09b0a3aafb
Add repetition_penalty
|
2 rokov pred |
|
callbacks.py
|
b246d17513
Fix `type object is not subscriptable`
|
2 rokov pred |
|
chat.py
|
dcf61a8897
"character greeting" displayed and editable on the fly (#743)
|
2 rokov pred |
|
deepspeed_parameters.py
|
f38c9bf428
Fix deepspeed (oops)
|
3 rokov pred |
|
extensions.py
|
1edfb96778
Fix loading extensions from within the interface
|
2 rokov pred |
|
html_generator.py
|
8579fe51dd
Fix new lines in the HTML tab
|
2 rokov pred |
|
llamacpp_model.py
|
2c52310642
Add --threads flag for llama.cpp
|
2 rokov pred |
|
models.py
|
3a47a602a3
Detect ggml*.bin files automatically
|
2 rokov pred |
|
shared.py
|
b24147c7ca
Document --pre_layer
|
2 rokov pred |
|
text_generation.py
|
b0890a7925
Add shared.is_chat() function
|
2 rokov pred |
|
training.py
|
2a267011dc
Use Path.stem for simplicity
|
2 rokov pred |
|
ui.py
|
d30a14087f
Further reorganize the UI
|
2 rokov pred |
OWKenobi
ee4547cd34
Detect "vicuna" as llama model type (#772)