Commit Graph

569 Commits

Author SHA1 Message Date
Vivek Khandelwal
d7092aafaa Fix multiple issue for Langchain
This commit fixes the following issue for the Langchain:
1.) Web UI not able to fetch results.
2.) For each query model getting reloaded.
3.) SHARK module not using user provided device and precision.
4.) Create a class for main Langchain code.
5.) Misc issues
2023-07-21 21:56:27 +05:30
Vivek Khandelwal
a415f3f70e Fix Langchain Prompt issue and add web UI support (#1682) 2023-07-21 06:36:55 -07:00
Vivek Khandelwal
c292e5c9d7 Add Langchain CPU support and update requirements 2023-07-20 18:53:34 +05:30
Vivek Khandelwal
03c4d9e171 Add support for Llama-2-70b for web and cli, and for hf_auth_token 2023-07-20 14:57:48 +05:30
jinchen62
3662224c04 Update brevitas requirement (#1677)
also clean up useless args

Co-authored-by: powderluv <powderluv@users.noreply.github.com>
2023-07-19 22:03:32 -07:00
Vivek Khandelwal
db3f222933 Revert "Add Llama2 70B option in CLI and WebUI (#1673)" (#1679)
This reverts commit 41e5088908.
2023-07-19 22:02:48 -07:00
Stefan Kapusniak
68b3021325 Fixes cosmetic problems with Gradio 3.37.0 (#1676)
* Fix nod-ai logo having a white border
* Fix control labels having a black background
* Remove extra lower border below Save Prompt checkboxes in Txt2Img UI
2023-07-19 17:28:53 -07:00
AyaanShah2204
336469154d added copy-metadata for pyyaml (#1678) 2023-07-19 17:27:25 -07:00
Abhishek Varma
41e5088908 Add Llama2 70B option in CLI and WebUI (#1673) 2023-07-19 10:41:42 -07:00
PhaneeshB
0a8f7673f4 Add README for CodeGen server 2023-07-19 23:10:23 +05:30
PhaneeshB
c482ab78da fix second vic clearing for low mem device 2023-07-19 23:10:23 +05:30
Vivek Khandelwal
4be80f7158 Add support for the Llama-2 model 2023-07-19 20:57:08 +05:30
Daniel Garvey
8927cb0a2c set optional vmfb download (#1667) 2023-07-18 10:57:28 -07:00
Daniel Garvey
8c317e4809 fix cli for vicuna (#1666) 2023-07-18 10:03:40 -07:00
Vivek Khandelwal
b0136593df Add support for different compilation paths for DocuChat (#1665) 2023-07-18 09:49:44 -07:00
powderluv
14559dd620 Update DocuChat as experimental (#1660) 2023-07-17 22:12:05 -07:00
AyaanShah2204
22a4254adf fixed pyinstaller path for langchain imports (#1658) 2023-07-17 12:19:21 -07:00
Vivek Khandelwal
ab01f0f048 Add Langchain model in SHARK (#1657)
* Add H2OGPT

* Add UI tab for h2ogpt

* Add source files from h2ogpt

* Add the rest of the files

* Add h2ogpt support

* Add SHARK Compilation support for langchain model for cli mode

---------

Co-authored-by: George Petterson <gpetters@protonmail.com>
2023-07-17 09:58:15 -07:00
Phaneesh Barwaria
c471d17cca codegen API (#1655) 2023-07-16 20:00:39 -07:00
Stefan Kapusniak
a2a436eb0c SD - Add repeatable (batch) seeds option (#1654)
* Generates the seeds for all batch_count batches being run up front
rather than generating the seed for a batch just before it is run.
* Adds a --repeatable_seeds argument defaulting to False
* When repeatable_seeds=True, the first seed for a set of batches will
also be used as the rng seed for the subsequent batch seeds in the run.
The rng seed is then reset.
* When repeatable_seeds=False, batch seeding works as currently.
* Update scripts under apps/scripts that support the batch_count
argument to also support the repeatable_seeds argument.
* UI/Web: Adds a checkbox element on each SD tab after batch count/size
for toggling repeatable seeds, and update _inf functions to take
this into account.
* UI/Web: Moves the Stop buttons out of the Advanced sections and next
to Generate to make things not fit quite so badly with the extra UI
elements.
* UI/Web: Fixes logging to the upscaler output text box not working
correctly when running multiple batches.
2023-07-15 16:22:41 -07:00
jinchen62
e20cd71314 Change to a separate pass to unpack quantized weights (#1652) 2023-07-15 04:54:53 -07:00
powderluv
5ec91143f5 add a HF accelerate requirement (#1651) 2023-07-14 05:56:12 -07:00
jinchen62
91027f8719 Remove done TODOs, a sup PR for #1644 (#1647) 2023-07-12 23:30:45 -07:00
powderluv
a909fc2e78 add tiktoken to spec file (#1646) 2023-07-12 16:12:02 -07:00
jinchen62
247f69cf9d Apply canonicalize for unpacking int4 (#1644)
- tested it unpacks int4 as expected
- tested it doesn't make difference on int8
2023-07-11 19:41:09 -07:00
PhaneeshB
3b8f7cc231 Add codegen support in UI + lint 2023-07-11 21:58:01 +05:30
PhaneeshB
6e8dbf72bd mlir/vmfb path fixes for vic pipeline 2023-07-11 21:58:01 +05:30
PhaneeshB
38e5b62d80 adapt UI to send model details to pipeline 2023-07-11 21:58:01 +05:30
PhaneeshB
1c7eecc981 add codegen support in vic pipeline 2023-07-11 21:58:01 +05:30
PhaneeshB
be417f0bf4 fix precision for fp16 2023-07-11 21:58:01 +05:30
AyaanShah2204
a517e217b0 Added support for building ZIP distributions (#1639)
* added support for zip files

* making linter happy

* Added temporary fix for NoneType padding

* Removed zip script

* Added shared imports file

* making linter happy
2023-07-09 06:45:36 -07:00
Ranvir Singh Virk
9fcae4f808 Metal testing (#1595)
* Fixing metal_platform and device selection

* fixing for metal platform

* fixed for black lint formating
2023-07-08 15:22:53 -07:00
Stefan Kapusniak
788d469c5b UI/Web Refix remaining gradio deprecation warning (#1638) 2023-07-08 13:48:36 -07:00
Stefan Kapusniak
8a59f7cc27 UI/Web add 'open folder' button to output gallery (#1634)
* Adds a button that opens the currently selected subdirectory using
the default OS file manager
* Improve output gallery handling of having images deleted out from
under it.
* Don't show VAE or LoRA lines in parameter info panel when their
value is 'None'
* Use a css class for small icon buttons on the output gallery
tab instead using the same id for multiple buttons
2023-07-08 12:44:59 -07:00
Stefan Kapusniak
1c2ec3c7a2 Some Fixes for Gradio 3.36.1 (#1637)
* Clear .style deprecation warnings.
* Re-remove download button from Nod logos.
* Add work around for `container=false` not doing what it did before on
dropdowns to the output gallery CSS
2023-07-08 11:20:34 -07:00
jinchen62
47ec7275e6 Fix brevitas quantize argument (#1633) 2023-07-07 11:30:31 -07:00
powderluv
1f72907886 Fix the pyinstaller for chatbots (#1631) 2023-07-06 23:30:01 -07:00
Daniel Garvey
06c8aabd01 remove local-sync from webui (#1629) 2023-07-06 13:58:59 -07:00
Phaneesh Barwaria
55a12cc0c4 cpu name in device (#1628)
* show cpu name in devices

* change device order for chatbot
2023-07-06 12:00:09 -07:00
Abhishek Varma
1b62dc4529 [Vicuna] Revert the formatting for Brevitas op (#1626)
-- This commit reverts the formatting for Brevitas op.
-- It also excludes vicuna.py script from `black` formatter.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2023-07-06 06:56:17 -07:00
Daniel Garvey
c5a47887f4 Revert revert negative prompt change (#1625)
* revert default flag changes

* revert revert negative prompt change

* revert revert negative prompt change
2023-07-05 22:09:06 -07:00
Daniel Garvey
c72d0eaf87 revert default flag changes (#1622) 2023-07-05 15:43:26 -05:00
xzuyn
043e5a5c7a fix a mistake I made, and more formatting changes, and add ++/Karras (#1619)
* fixed missing line break in `stablelm_ui.py` `start_message`
- also more formatting changes

* fix variable spelling mistake

* revert some formatting cause black wants it different

* one less line, still less than 79

* add ++, karras, and karras++ types of dpmsolver.

* black line length 79

---------

Co-authored-by: powderluv <powderluv@users.noreply.github.com>
2023-07-05 09:00:16 -07:00
Abhishek Varma
a1b1ce935c int8 e2e for WebUI (#1620) 2023-07-05 07:08:36 -07:00
jinchen62
bc6fee1a0c Add int4/int8 vicuna (#1598) 2023-07-05 07:01:51 -07:00
xzuyn
91ab594744 minor fix, some changes, some additions, and cleaning up (#1618)
* - fix overflowing text (a janky fix)
- add DEISMultistep scheduler as an option
- set default scheduler to DEISMultistep
- set default CFG to 3.5
- set default steps to 16
- add `xzuyn/PhotoMerge` as a model option
- add 3 new example prompts (which work nicely with PhotoMerge)
- formatting

* Set DEISMultistep in the cpu_only list instead

* formatting

* formatting

* modify prompts

* resize window to 81% & 85% monitor resolution instead of (WxH / 1.0625).

* increase steps to 32 after some testing. somewhere in between 16 and 32 is best compromise on speed/quality for DEIS, so 32 steps to play it safe.

* black line length 79

* revert settings DEIS as default scheduler.

* add more schedulers & revert accidental DDIM change
- add DPMSolverSingleStep, KDPM2AncestralDiscrete, & HeunDiscrete.
- did not add `DPMSolverMultistepInverse` or `DDIMInverse` as they only output latent noise, there are a few I did not try adding yet.
- accidentally set `upscaler_ui.py` to EulerDiscrete by default last commit while reverting DEIS changes.
- add `xzuyn/PhotoMerge-inpainting` as an in or out painting model.

* black line length 79

* add help section stuff and some other changes
- list the rest of the schedulers in argument help section.
- replace mutable default arguments.
- increased default window height to 91% to remove any scrolling for the main txt2img page (tested on a 1920x1080 monitor). width is the same as its just enough to have the image output on the side instead of the bottom.
- cleanup
2023-07-04 18:51:23 -07:00
Eliasj42
4015793f84 changed method of compiling vicuna to remove first and second vicuna (#1611)
Co-authored-by: Elias Joseph <elias@nod-labs.com>
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
2023-07-03 12:12:43 -07:00
Ean Garvey
d63ce76dd8 Use sortable image filenames for SD outputs. (#1528) 2023-07-03 10:30:47 -07:00
Ean Garvey
6d286c0609 Enable tuning for rectangle sizes on rdna2. (#1608) 2023-06-30 22:28:24 -07:00
Stefan Kapusniak
7392b22731 UI/Web Reduce animation of default --progress_bars (#1613) 2023-06-30 21:12:10 -07:00