| .. |
|
GPTQ_loader.py
|
1cb9246160
Adapt to the new model names
|
2 jaren geleden |
|
LoRA.py
|
a21e580782
Move an import
|
2 jaren geleden |
|
RWKV.py
|
09b0a3aafb
Add repetition_penalty
|
2 jaren geleden |
|
callbacks.py
|
b246d17513
Fix `type object is not subscriptable`
|
2 jaren geleden |
|
chat.py
|
5f3f3faa96
Better handle CUDA out of memory errors in chat mode
|
2 jaren geleden |
|
deepspeed_parameters.py
|
f38c9bf428
Fix deepspeed (oops)
|
3 jaren geleden |
|
extensions.py
|
1edfb96778
Fix loading extensions from within the interface
|
2 jaren geleden |
|
html_generator.py
|
8579fe51dd
Fix new lines in the HTML tab
|
2 jaren geleden |
|
llamacpp_model.py
|
2c52310642
Add --threads flag for llama.cpp
|
2 jaren geleden |
|
models.py
|
3a47a602a3
Detect ggml*.bin files automatically
|
2 jaren geleden |
|
shared.py
|
b0890a7925
Add shared.is_chat() function
|
2 jaren geleden |
|
text_generation.py
|
b0890a7925
Add shared.is_chat() function
|
2 jaren geleden |
|
training.py
|
58349f44a0
Handle training exception for unsupported models
|
2 jaren geleden |
|
ui.py
|
d30a14087f
Further reorganize the UI
|
2 jaren geleden |
oobabooga
5f3f3faa96
Better handle CUDA out of memory errors in chat mode