 oobabooga
|
cdfa787bcb
Update README
|
2 年之前 |
|
oobabooga
|
3bda907727
Merge pull request #366 from oobabooga/lora
|
2 年之前 |
|
oobabooga
|
614dad0075
Remove unused import
|
2 年之前 |
|
oobabooga
|
a717fd709d
Sort the imports
|
2 年之前 |
|
oobabooga
|
7d97287e69
Update settings-template.json
|
2 年之前 |
|
oobabooga
|
29fe7b1c74
Remove LoRA tab, move it into the Parameters menu
|
2 年之前 |
|
oobabooga
|
214dc6868e
Several QoL changes related to LoRA
|
2 年之前 |
|
oobabooga
|
4c130679c7
Merge pull request #377 from askmyteapot/Fix-Multi-gpu-GPTQ-Llama-no-tokens
|
2 年之前 |
 askmyteapot
|
53b6a66beb
Update GPTQ_Loader.py
|
2 年之前 |
|
oobabooga
|
0cecfc684c
Add files
|
2 年之前 |
|
oobabooga
|
104293f411
Add LoRA support
|
2 年之前 |
|
oobabooga
|
ee164d1821
Don't split the layers in 8-bit mode by default
|
2 年之前 |
|
oobabooga
|
0a2aa79c4e
Merge pull request #358 from mayaeary/8bit-offload
|
2 年之前 |
|
oobabooga
|
e085cb4333
Small changes
|
2 年之前 |
|
oobabooga
|
dd1c5963da
Update README
|
2 年之前 |
|
oobabooga
|
38d7017657
Add all command-line flags to "Interface mode"
|
2 年之前 |
 awoo
|
83cb20aad8
Add support for --gpu-memory witn --load-in-8bit
|
2 年之前 |
|
oobabooga
|
23a5e886e1
The LLaMA PR has been merged into transformers
|
2 年之前 |
|
oobabooga
|
d54f3f4a34
Add no-stream checkbox to the interface
|
2 年之前 |
|
oobabooga
|
1c378965e1
Remove unused imports
|
2 年之前 |
|
oobabooga
|
a577fb1077
Keep GALACTICA special tokens (#300)
|
2 年之前 |
|
oobabooga
|
25a00eaf98
Add "Experimental" warning
|
2 年之前 |
|
oobabooga
|
599d3139fd
Increase the reload timeout a bit
|
2 年之前 |
|
oobabooga
|
4d64a57092
Add Interface mode tab
|
2 年之前 |
|
oobabooga
|
b50172255a
Merge branch 'main' of github.com:oobabooga/text-generation-webui
|
2 年之前 |
|
oobabooga
|
ffb898608b
Mini refactor
|
2 年之前 |
|
oobabooga
|
d3a280e603
Merge pull request #348 from mayaeary/feature/koboldai-api-share
|
2 年之前 |
|
oobabooga
|
445ebf0ba8
Update README.md
|
2 年之前 |
|
awoo
|
0552ab2e9f
flask_cloudflared for shared tunnels
|
2 年之前 |
|
oobabooga
|
e9e76bb06c
Delete WSL.md
|
2 年之前 |
