 Thomas Antony
|
7fa5d96c22
Update to use new llamacpp API
|
il y a 2 ans |
|
Thomas Antony
|
79fa2b6d7e
Add support for alpaca
|
il y a 2 ans |
|
Thomas Antony
|
8953a262cb
Add llamacpp to requirements.txt
|
il y a 2 ans |
|
Thomas Antony
|
a5f5736e74
Add to text_generation.py
|
il y a 2 ans |
|
Thomas Antony
|
7745faa7bb
Add llamacpp to models.py
|
il y a 2 ans |
|
Thomas Antony
|
7a562481fa
Initial version of llamacpp_model.py
|
il y a 2 ans |
|
Thomas Antony
|
53ab1e285d
Update .gitignore
|
il y a 2 ans |
 oobabooga
|
f0fdab08d3
Increase --chat height
|
il y a 2 ans |
|
oobabooga
|
bd65940a48
Increase --chat box height
|
il y a 2 ans |
|
oobabooga
|
131753fcf5
Save the sha256sum of downloaded models
|
il y a 2 ans |
|
oobabooga
|
a21e580782
Move an import
|
il y a 2 ans |
|
oobabooga
|
55755e27b9
Don't hardcode prompts in the settings dict/json
|
il y a 2 ans |
|
oobabooga
|
1cb9246160
Adapt to the new model names
|
il y a 2 ans |
|
oobabooga
|
0345e04249
Fix "Unknown argument(s): {'verbose': False}"
|
il y a 2 ans |
|
oobabooga
|
9104164297
Merge pull request #618 from nikita-skakun/optimize-download-model
|
il y a 2 ans |
|
oobabooga
|
37754164eb
Move argparse
|
il y a 2 ans |
|
oobabooga
|
6403e72062
Merge branch 'main' into nikita-skakun-optimize-download-model
|
il y a 2 ans |
|
oobabooga
|
1445ea86f7
Add --output and better metadata for downloading models
|
il y a 2 ans |
|
oobabooga
|
58349f44a0
Handle training exception for unsupported models
|
il y a 2 ans |
|
oobabooga
|
a6d0373063
Fix training dataset loading #636
|
il y a 2 ans |
|
oobabooga
|
41b58bc47e
Update README.md
|
il y a 2 ans |
|
oobabooga
|
3b4447a4fe
Update README.md
|
il y a 2 ans |
|
oobabooga
|
5d0b83c341
Update README.md
|
il y a 2 ans |
|
oobabooga
|
c2a863f87d
Mention the updated one-click installer
|
il y a 2 ans |
|
oobabooga
|
1edfb96778
Fix loading extensions from within the interface
|
il y a 2 ans |
 Nikita Skakun
|
aaa218a102
Remove unused import.
|
il y a 2 ans |
|
Nikita Skakun
|
ff515ec2fe
Improve progress bar visual style
|
il y a 2 ans |
|
oobabooga
|
304f812c63
Gracefully handle CUDA out of memory errors with streaming
|
il y a 2 ans |
|
Nikita Skakun
|
4d8e101006
Refactor download process to use multiprocessing
|
il y a 2 ans |
|
oobabooga
|
b2f356a9ae
Generalize GPTQ_loader, support any model (#615 from mayaeary/feature/gpt-j-4bit-v2)
|
il y a 2 ans |
