Commit graph

4219 commits

Author SHA1 Message Date
oobabooga 0ef1b8f8b4 Use ExLlamaV2 (instead of the HF one) for EXL2 models for now
It doesn't seem to have the "OverflowError" bug
2025-04-17 05:47:40 -07:00
oobabooga 38dc09dca5 Bump exllamav3 to the latest commit 2025-04-15 09:50:36 -07:00
oobabooga 038a012581 Installer: Remove .installer_state.json on reinstalling 2025-04-11 21:12:32 -07:00
oobabooga 682c78ea42 Add back detection of GPTQ models (closes #6841) 2025-04-11 21:00:42 -07:00
oobabooga 454366f93e Change the ExLlamaV3 wheel version to 0.0.1a1 2025-04-10 18:33:29 -07:00
oobabooga d7b336d37e Update the README 2025-04-09 20:12:14 -07:00
oobabooga 4ed0da74a8 Remove the obsolete 'multimodal' extension 2025-04-09 20:09:48 -07:00
oobabooga 598568b1ed Revert "UI: remove the streaming cursor"
This reverts commit 6ea0206207.
2025-04-09 16:03:14 -07:00
oobabooga 297a406e05 UI: smoother chat streaming
This removes the throttling associated to gr.Textbox that made words appears in chunks rather than one at a time
2025-04-09 16:02:37 -07:00
oobabooga 6ea0206207 UI: remove the streaming cursor 2025-04-09 14:59:34 -07:00
oobabooga 9025848df5 Small change to installer 2025-04-09 10:25:47 -07:00
oobabooga d337ea31fa Revert "Reapply "Update transformers requirement from ==4.50.* to ==4.51.* (#6834)""
This reverts commit 8229736ec4.
2025-04-09 10:16:47 -07:00
oobabooga 8229736ec4 Reapply "Update transformers requirement from ==4.50.* to ==4.51.* (#6834)"
This reverts commit 0b3503c91f.
2025-04-09 08:38:06 -07:00
oobabooga 89f40cdcf7 Update libstdcxx-ng for GLIBCXX_3.4.30 support on Linux 2025-04-09 08:28:44 -07:00
oobabooga ad1ada6574 Change one message in the installer 2025-04-09 05:17:10 -07:00
oobabooga d8aad6da94 Fix an update bug 2025-04-08 20:20:24 -07:00
oobabooga 8b8d39ec4e
Add ExLlamaV3 support (#6832) 2025-04-09 00:07:08 -03:00
oobabooga 0b3503c91f Revert "Update transformers requirement from ==4.50.* to ==4.51.* (#6834)"
This reverts commit f1f32386b4.
2025-04-08 12:26:03 -07:00
oobabooga 649ee729c1 Remove Python 3.10 support 2025-04-08 09:22:06 -07:00
oobabooga bf48ec8c44 Remove an unnecessary UI message 2025-04-07 17:43:41 -07:00
oobabooga a5855c345c
Set context lengths to at most 8192 by default (to prevent out of memory errors) (#6835) 2025-04-07 21:42:33 -03:00
dependabot[bot] f1f32386b4
Update transformers requirement from ==4.50.* to ==4.51.* (#6834) 2025-04-07 19:29:39 -03:00
oobabooga 204db28362 Update the dockerfiles 2025-04-06 18:48:31 -07:00
oobabooga eef90a4964 Update some intel arc installation commands 2025-04-06 17:44:07 -07:00
oobabooga a8a64b6c1c Update the README 2025-04-06 17:40:18 -07:00
oobabooga c010cea7be Remove CUDA 11.8 support 2025-04-06 17:17:25 -07:00
Shixian Sheng cbffcf67ef
Fix links in the ngrok extension README (#6826) 2025-04-02 14:28:29 -03:00
dependabot[bot] 77a73cc561
Update peft requirement from ==0.12.* to ==0.15.* (#6820) 2025-03-31 21:01:27 -03:00
oobabooga 109de34e3b Remove the old --model-menu flag 2025-03-31 09:24:03 -07:00
oobabooga 1981327285 Fix the colab notebook 2025-03-29 19:17:14 -07:00
oobabooga 79a26d7a5c Lint 2025-03-29 18:49:48 -07:00
oobabooga 1bd208c219
Add a new chat style: Dark (#6817) 2025-03-29 22:47:10 -03:00
oobabooga 525b1e0207 Remove the stalebot 2025-03-29 13:43:16 -07:00
dependabot[bot] 2bfaf44df0
Update accelerate requirement from ==1.4.* to ==1.5.* (#6802) 2025-03-26 10:03:21 -03:00
oobabooga 01e42a00ff Bump transformers to 4.50 2025-03-26 06:01:57 -07:00
oobabooga 758c3f15a5 Lint 2025-03-14 20:04:43 -07:00
SeanScripts 60d67994d9
Perplexity colors extension updates (#6764) 2025-03-14 16:45:53 -03:00
oobabooga 5bcd2d7ad0
Add the top N-sigma sampler (#6796) 2025-03-14 16:45:11 -03:00
oobabooga 677d74a6a0 Revert "UI: improved scrollbar styles", add just a small change instead 2025-03-14 12:10:48 -07:00
oobabooga 6ab04698f6 UI: improve the light mode left sidebar color 2025-03-14 12:03:49 -07:00
oobabooga 26317a4c7e Fix jinja2 error while loading c4ai-command-a-03-2025 2025-03-14 10:59:05 -07:00
oobabooga f04a37adc2 UI: improved scrollbar styles 2025-03-14 05:20:15 -07:00
oobabooga 0261338910 Bump llama-cpp-python to 0.3.8 2025-03-12 17:55:25 -07:00
oobabooga 39fded487a Bump ExllamaV2 to 0.2.8 2025-03-12 17:54:30 -07:00
dependabot[bot] a12e05d9c0
Bump jinja2 from 3.1.5 to 3.1.6 (#6786) 2025-03-12 16:11:03 -03:00
Kelvie Wong 16fa9215c4
Fix OpenAI API with new param (show_after), closes #6747 (#6749)
---------

Co-authored-by: oobabooga <oobabooga4@gmail.com>
2025-02-18 12:01:30 -03:00
SeanScripts b131f86584
Perplexity colors extension v2 (#6756) 2025-02-18 11:56:28 -03:00
Alireza Ghasemi 01f20d2d9f
Improve SuperboogaV2 with Date/Time Embeddings, GPU Support, and Multiple File Formats (#6748) 2025-02-17 22:38:15 -03:00
dependabot[bot] 12f6f7ba9f
Update accelerate requirement from ==1.3.* to ==1.4.* (#6753) 2025-02-17 22:35:38 -03:00
oobabooga dba17c40fc Make transformers 4.49 functional 2025-02-17 17:31:11 -08:00