oobabooga
193fe18c8c
Resolve conflicts
2023-09-21 17:45:11 -07:00
oobabooga
df39f455ad
Merge remote-tracking branch 'second-repo/main' into merge-second-repo
2023-09-21 17:39:54 -07:00
oobabooga
fc2b831692
Basic changes
2023-09-21 15:55:09 -07:00
oobabooga
b04b3957f9
Move one-click-installers into the repository
2023-09-21 15:35:53 -07:00
oobabooga
b74bf5638b
Install extensions dependencies before webui dependencies
...
webui takes precedence over extensions.
2023-08-14 09:15:25 -07:00
jllllll
28e3ce4317
Simplify GPTQ-for-LLaMa installation ( #122 )
2023-08-10 13:19:47 -03:00
oobabooga
fa4a948b38
Allow users to write one flag per line in CMD_FLAGS.txt
2023-08-09 01:58:23 -03:00
oobabooga
601fc424cd
Several improvements ( #117 )
2023-08-03 14:39:46 -03:00
jllllll
aca5679968
Properly fix broken gcc_linux-64 package ( #115 )
2023-08-02 23:39:07 -03:00
jllllll
ecd92d6a4e
Remove unused variable from ROCm GPTQ install ( #107 )
2023-07-26 22:16:36 -03:00
jllllll
1e3c950c7d
Add AMD GPU support for Linux ( #98 )
2023-07-26 17:33:02 -03:00
jllllll
52e3b91f5e
Fix broken gxx_linux-64 package. ( #106 )
2023-07-26 01:55:08 -03:00
oobabooga
cc2ed46d44
Make chat the default again
2023-07-20 18:55:09 -03:00
jllllll
fcb215fed5
Add check for compute support for GPTQ-for-LLaMa ( #104 )
...
Installs from main cuda repo if fork not supported
Also removed cuBLAS llama-cpp-python installation in preperation for 4b19b74e6c
2023-07-20 11:11:00 -03:00
jllllll
4df3f72753
Fix GPTQ fail message not being shown on update ( #103 )
2023-07-19 22:25:09 -03:00
jllllll
11a8fd1eb9
Add cuBLAS llama-cpp-python wheel installation ( #102 )
...
Parses requirements.txt using regex to determine required version.
2023-07-16 01:31:33 -03:00
oobabooga
bb79037ebd
Fix wrong pytorch version on Linux+CPU
...
It was installing nvidia wheels
2023-07-07 20:40:31 -03:00
oobabooga
564a8c507f
Don't launch chat mode by default
2023-07-07 13:32:11 -03:00
jllllll
eac8450ef7
Move special character check to start script ( #92 )
...
Also port print_big_message function to batch
2023-06-24 10:06:35 -03:00
jllllll
04cae3e5db
Remove bitsandbytes compatibility workaround ( #91 )
...
New bnb does not need it.
Commented out in case it is needed in the futute.
2023-06-21 15:40:41 -03:00
oobabooga
80a615c3ae
Add space
2023-06-20 22:48:45 -03:00
oobabooga
a2116e8b2b
use uninstall -y
2023-06-20 21:24:01 -03:00
oobabooga
c0a1baa46e
Minor changes
2023-06-20 20:23:21 -03:00
jllllll
5cbc0b28f2
Workaround for Peft not updating their package version on the git repo ( #88 )
...
* Workaround for Peft not updating their git package version
* Update webui.py
---------
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2023-06-20 20:21:10 -03:00
jllllll
9bb2fc8cd7
Install Pytorch through pip instead of Conda ( #84 )
2023-06-20 16:39:23 -03:00
jllllll
b1d05cbbf6
Install exllama ( #83 )
...
* Install exllama
* Handle updating exllama
2023-06-17 19:10:36 -03:00
jllllll
b2483e28d1
Check for special characters in path on Windows ( #81 )
...
Display warning message if detected
2023-06-17 19:09:22 -03:00
oobabooga
5540335819
Better way to detect if a model has been downloaded
2023-06-01 14:01:19 -03:00
oobabooga
248ef32358
Print a big message for CPU users
2023-06-01 01:40:24 -03:00
oobabooga
290a3374e4
Don't download a model during installation
...
And some other updates/minor improvements
2023-06-01 01:30:21 -03:00
Sam
dea1bf3d04
Parse g++ version instead of using string matching ( #72 )
2023-05-31 14:44:36 -03:00
gavin660
97bc7e3fb6
Adds functionality for user to set flags via environment variable ( #59 )
2023-05-31 14:43:22 -03:00
Sam
5405635305
Install pre-compiled wheels for Linux ( #74 )
2023-05-31 14:41:54 -03:00
jllllll
be98e74337
Install older bitsandbytes on older gpus + fix llama-cpp-python issue ( #75 )
2023-05-31 14:41:03 -03:00
oobabooga
c8ce2e777b
Add instructions for CPU mode users
2023-05-25 10:57:52 -03:00
oobabooga
996c49daa7
Remove bitsandbytes installation step
...
Following 548f05e106
2023-05-25 10:50:20 -03:00
jllllll
4ef2de3486
Fix dependencies downgrading from gptq install ( #61 )
2023-05-18 12:46:04 -03:00
oobabooga
07510a2414
Change a message
2023-05-18 10:58:37 -03:00
oobabooga
0bcd5b6894
Soothe anxious users
2023-05-18 10:56:49 -03:00
oobabooga
1309cdd257
Add a space
2023-05-10 18:03:12 -03:00
oobabooga
3e19733d35
Remove obsolete comment
2023-05-10 18:01:04 -03:00
oobabooga
d7d3f7f31c
Add a "CMD_FLAGS" variable
2023-05-10 17:54:12 -03:00
oobabooga
b8cfc20e58
Don't install superbooga by default
2023-05-09 14:17:08 -03:00
Semjon Kravtšenko
126d216384
Fix possible crash ( #53 )
2023-05-06 01:14:09 -03:00
Blake Wyatt
4babb22f84
Fix/Improve a bunch of things ( #42 )
2023-05-02 12:28:20 -03:00
oobabooga
a4f6724b88
Add a comment
2023-04-24 16:47:22 -03:00
oobabooga
9a8487097b
Remove --auto-devices
2023-04-24 16:43:52 -03:00
Blake Wyatt
6d2c72b593
Add support for MacOS, Linux, and WSL ( #21 )
...
* Initial commit
* Initial commit with new code
* Add comments
* Move GPTQ out of if
* Fix install on Arch Linux
* Fix case where install was aborted
If the install was aborted before a model was downloaded, webui wouldn't run.
* Update start_windows.bat
Add necessary flags to Miniconda installer
Disable Start Menu shortcut creation
Disable ssl on Conda
Change Python version to latest 3.10,
I've noticed that explicitly specifying 3.10.9 can break the included Python installation
* Update bitsandbytes wheel link to 0.38.1
Disable ssl on Conda
* Add check for spaces in path
Installation of Miniconda will fail in this case
* Mirror changes to mac and linux scripts
* Start with model-menu
* Add updaters
* Fix line endings
* Add check for path with spaces
* Fix one-click updating
* Fix one-click updating
* Clean up update scripts
* Add environment scripts
---------
Co-authored-by: jllllll <3887729+jllllll@users.noreply.github.com>
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2023-04-18 02:23:09 -03:00
