oobabooga
290a3374e4
Don't download a model during installation
...
And some other updates/minor improvements
2023-06-01 01:30:21 -03:00
oobabooga
2e53caa806
Create LICENSE
2023-05-31 16:28:36 -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
jllllll
b1b3bb6923
Improve environment isolation ( #68 )
2023-05-25 11:15:05 -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
4ab5deeea0
Update INSTRUCTIONS.TXT
2023-05-10 18:00:37 -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
jllllll
29727c6502
Fix Windows PATH fix ( #57 )
2023-05-09 01:49:27 -03:00
Semjon Kravtšenko
126d216384
Fix possible crash ( #53 )
2023-05-06 01:14:09 -03:00
Roberts Slisans
dec31af910
Create .gitignore ( #43 )
2023-05-02 23:47:19 -03:00
Semih Aslan
24c5ba2b9c
Fixed error when $OS_ARCH returns aarch64 ( #45 )
...
For some machines $OS_ARCH returns aarch64 instead of ARM64,and as i see here this should fix it.
2023-05-02 23:47:03 -03:00
Blake Wyatt
4babb22f84
Fix/Improve a bunch of things ( #42 )
2023-05-02 12:28:20 -03:00
oobabooga
bcd5786a47
Add files via upload
2023-04-24 16:53:04 -03:00
oobabooga
d66059d95a
Update INSTRUCTIONS.TXT
2023-04-24 16:50:03 -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
oobabooga
dfbb18610f
Update INSTRUCTIONS.TXT
2023-04-23 12:58:14 -03:00
oobabooga
1ba0082410
Add files via upload
2023-04-18 02:30:47 -03:00
oobabooga
a5f7d98cf3
Rename environment_windows.bat to cmd_windows.bat
2023-04-18 02:30:23 -03:00
oobabooga
316aaff348
Rename environment_macos.sh to cmd_macos.sh
2023-04-18 02:30:08 -03:00
oobabooga
647f7bca36
Rename environment_linux.sh to cmd_linux.sh
2023-04-18 02:29:55 -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
jllllll
254609daca
Update llama-cpp-python link to official wheel ( #19 )
2023-04-10 10:48:56 -03:00
jllllll
c3e1a58cb3
Correct llama-cpp-python wheel link ( #17 )
2023-04-09 23:46:54 -03:00
oobabooga
97840c92f9
Add working llamaa-cpp-python install from wheel. ( #13 from Loufe/oobabooga-windows)
2023-04-09 23:23:27 -03:00
Lou Bernardi
0818bc93ad
Add working llamaa-cpp-python install from wheel.
2023-04-08 22:44:55 -04:00
oobabooga
ef0f748618
Prevent CPU version of Torch from being installed ( #10 from jllllll/oobabooga-windows)
2023-04-06 13:54:14 -03:00
jllllll
1e656bef25
Specifically target cuda 11.7 ver. of torch 2.0.0
...
Move conda-forge channel to global list of channels
Hopefully prevents missing or incorrect packages
2023-04-05 16:52:05 -05:00
jllllll
5aaf771c7d
Add additional sanity check
...
Add environment creation error
Improve error visibility
2023-04-04 12:31:26 -05:00
oobabooga
9b4e9a98f0
Merge pull request #9 from jllllll/oobabooga-windows
...
Add -k flag to curl command
2023-04-03 00:31:14 -03:00
jllllll
c86d3e9c74
Add -k flag to curl command
...
Disables SSL certificate verification which was causing curl to fail on some systems.
https://github.com/oobabooga/text-generation-webui/issues/644#issuecomment-1493518391
2023-04-02 21:28:04 -05:00
oobabooga
e3c348e42b
Add .git
2023-04-02 01:11:05 -03:00
oobabooga
b704fe7878
Use my fork of GPTQ-for-LLaMa for stability
2023-04-02 01:10:22 -03:00
oobabooga
75465fa041
Merge pull request #6 from jllllll/oobabooga-windows
...
Attempt to Improve Reliability
2023-03-31 11:27:23 -03:00
jllllll
e4e3c9095d
Add warning for long paths
2023-03-30 20:48:40 -05:00
jllllll
172035d2e1
Minor Correction
2023-03-30 20:44:56 -05:00
jllllll
0b4ee14edc
Attempt to Improve Reliability
...
Have pip directly download and install backup GPTQ wheel instead of first downloading through curl.
Install bitsandbytes from wheel compiled for Windows from modified source.
Add clarification of minor, intermittent issue to instructions.
Add system32 folder to end of PATH rather than beginning.
Add warning when installed under a path containing spaces.
2023-03-30 20:04:16 -05:00
oobabooga
85e4ec6e6b
Download the cuda branch directly
2023-03-30 18:22:48 -03:00
oobabooga
78c0da4a18
Use the cuda branch of gptq-for-llama
...
Did I do this right @jllllll? This is because the current default branch (triton) is not compatible with Windows.
2023-03-30 18:04:05 -03:00
oobabooga
0de4f24b12
Merge pull request #4 from jllllll/oobabooga-windows
...
Change Micromamba download link
2023-03-29 09:49:32 -03:00
