| .. |
|
GPTQ_loader.py
|
39f3fec913
Broaden GPTQ-for-LLaMA branch support (#820)
|
2 rokov pred |
|
LoRA.py
|
a21e580782
Move an import
|
2 rokov pred |
|
RWKV.py
|
09b0a3aafb
Add repetition_penalty
|
2 rokov pred |
|
api.py
|
3f3e42e26c
Refactor several function calls and the API
|
2 rokov pred |
|
callbacks.py
|
b246d17513
Fix `type object is not subscriptable`
|
2 rokov pred |
|
chat.py
|
e94ab5dac1
Minor fixes
|
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
|
8203ce0cac
Stop character pic from being cached when changing chars or clearing. (#798)
|
2 rokov pred |
|
llamacpp_model.py
|
2c52310642
Add --threads flag for llama.cpp
|
2 rokov pred |
|
models.py
|
4ab679480e
allow quantized model to be loaded from model dir (#760)
|
2 rokov pred |
|
shared.py
|
378d21e80c
Add LLaMA-Precise preset (#767)
|
2 rokov pred |
|
text_generation.py
|
3f3e42e26c
Refactor several function calls and the API
|
2 rokov pred |
|
training.py
|
0c7ef26981
Lora trainer improvements (#763)
|
2 rokov pred |
|
ui.py
|
d30a14087f
Further reorganize the UI
|
2 rokov pred |
EyeDeck
39f3fec913
Broaden GPTQ-for-LLaMA branch support (#820)