Commit Graph

3066 Commits

Author SHA1 Message Date
oobabooga
0ee8d2b66b
Merge pull request #4627 from oobabooga/dev
Merge dev branch
2023-11-16 23:41:18 -03:00
oobabooga
780b00e1cf Minor bug fix 2023-11-16 18:39:39 -08:00
oobabooga
c0233bb9d3 Minor message change 2023-11-16 18:36:57 -08:00
oobabooga
94b7177174 Update docs/07 - Extensions 2023-11-16 18:24:46 -08:00
oobabooga
6525707a7f Fix "send instruction template to..." buttons (closes #4625) 2023-11-16 18:16:42 -08:00
oobabooga
510a01ef46 Lint 2023-11-16 18:03:06 -08:00
oobabooga
923c8e25fb
Bump llama-cpp-python to 0.2.18 (#4611) 2023-11-16 22:55:14 -03:00
Casper
61f429563e
Bump AutoAWQ to 0.1.7 (#4620) 2023-11-16 17:08:08 -03:00
oobabooga
e7d460d932 Make sure that API requirements are installed 2023-11-16 10:08:41 -08:00
oobabooga
cbf2b47476 Strip trailing "\" characters in CMD_FLAGS.txt 2023-11-16 09:33:36 -08:00
oobabooga
58c6001be9 Add missing exllamav2 samplers 2023-11-16 07:09:40 -08:00
oobabooga
cd41f8912b Warn users about n_ctx / max_seq_len 2023-11-15 18:56:42 -08:00
oobabooga
a475aa7816 Improve API documentation 2023-11-15 18:39:08 -08:00
oobabooga
9be48e83a9 Start API when "api" checkbox is checked 2023-11-15 16:35:47 -08:00
oobabooga
a85ce5f055 Add more info messages for truncation / instruction template 2023-11-15 16:20:31 -08:00
oobabooga
883701bc40 Alternative solution to 025da386a0
Fixes an error.
2023-11-15 16:04:02 -08:00
oobabooga
8ac942813c Revert "Fix CPU memory limit error (issue #3763) (#4597)"
This reverts commit 025da386a0.
2023-11-15 16:01:54 -08:00
oobabooga
e6f44d6d19 Print context length / instruction template to terminal when loading models 2023-11-15 16:00:51 -08:00
oobabooga
e05d8fd441 Style changes 2023-11-15 15:51:37 -08:00
oobabooga
be125e2708 Add /v1/internal/model/unload endpoint 2023-11-15 15:48:33 -08:00
David Nielson
564d0cde82
Use standard hyphens in filenames (#4576) 2023-11-15 20:29:00 -03:00
Andy Bao
025da386a0
Fix CPU memory limit error (issue #3763) (#4597)
get_max_memory_dict() was not properly formatting shared.args.cpu_memory

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2023-11-15 20:27:20 -03:00
Anton Rogozin
8a9d5a0cea
update AutoGPTQ to higher version for lora applying error fixing (#4604) 2023-11-15 20:23:22 -03:00
oobabooga
8a2af87d3a
Merge pull request #4608 from oobabooga/dev
Merge dev branch
2023-11-15 13:19:15 -03:00
oobabooga
072cfe19e9 Minor Colab fix 2023-11-15 08:18:32 -08:00
oobabooga
2337aebe4d
Merge pull request #4606 from oobabooga/dev
Merge dev branch
2023-11-15 13:16:44 -03:00
oobabooga
3d861a459d Minor Colab fix 2023-11-15 08:15:43 -08:00
oobabooga
dea90c7b67 Bump exllamav2 to 0.0.8 2023-11-13 10:34:10 -08:00
oobabooga
454fcf39a9
Merge pull request #4579 from oobabooga/dev
Merge dev branch
2023-11-13 11:39:08 -03:00
oobabooga
4f9bc63edf Installer: update a message for clarity 2023-11-10 09:43:02 -08:00
oobabooga
74fee4f312 Update Colab-TextGen-GPU.ipynb 2023-11-10 09:18:25 -08:00
oobabooga
52758f15da Remove sentence-transformers requirement (for #1575) 2023-11-10 07:35:29 -08:00
oobabooga
c5be3f7acb Make /v1/embeddings functional, add request/response types 2023-11-10 07:34:27 -08:00
oobabooga
7ed2143cd6
Update 12 - OpenAI API.md 2023-11-10 11:56:04 -03:00
oobabooga
0777b0d3c7 Add system_message parameter, document model (unused) parameter 2023-11-10 06:47:18 -08:00
oobabooga
4aabff3728 Remove old API, launch OpenAI API with --api 2023-11-10 06:39:08 -08:00
GuizzyQC
6a7cd01ebf
Fix bug with /internal/model/load (#4549)
Update shared.model_name after loading model through API call
2023-11-10 00:16:38 -03:00
oobabooga
2af7e382b1 Revert "Bump llama-cpp-python to 0.2.14"
This reverts commit 5c3eb22ce6.

The new version has issues:

https://github.com/oobabooga/text-generation-webui/issues/4540
https://github.com/abetlen/llama-cpp-python/issues/893
2023-11-09 10:02:13 -08:00
oobabooga
07d66e45b4
Merge pull request #4541 from oobabooga/dev
Merge dev branch
2023-11-09 14:53:34 -03:00
Ashley Kleynhans
372d712921
Fix deprecated API (#4539) 2023-11-09 14:51:50 -03:00
oobabooga
d86f1fd2c3 OpenAI API: stop streaming on client disconnect (closes #4521) 2023-11-09 06:37:32 -08:00
oobabooga
f7534b2f4b
Merge pull request #4532 from oobabooga/dev
Merge dev branch
2023-11-09 09:33:55 -03:00
oobabooga
effb3aef42 Prevent deadlocks in OpenAI API with simultaneous requests 2023-11-08 20:55:39 -08:00
oobabooga
4da00b6032
Merge pull request #4522 from oobabooga/dev
Merge dev branch
2023-11-08 22:57:08 -03:00
oobabooga
21ed9a260e Document the new "Custom system message" field 2023-11-08 17:54:10 -08:00
oobabooga
678fd73aef Document /v1/internal/model/load and fix a bug 2023-11-08 17:41:12 -08:00
MrMojoR
1754a3761b
Include trust remote code usage in openai api's embedder (#4513) 2023-11-08 11:25:43 -03:00
hronoas
6c7aad11f3
openai extension: wrong frequency_penalty type (#4512) 2023-11-08 11:23:51 -03:00
oobabooga
881e8a6e70
Small bug fix in /v1/internal/model/load 2023-11-08 02:34:13 -03:00
oobabooga
050ff36bd6 Revert "Add a comment to /v1/models"
This reverts commit 38b07493a0.
2023-11-07 21:09:47 -08:00