Commit Graph

4041 Commits

Author SHA1 Message Date
dependabot[bot]
9660f6f10e
Bump aqlm[cpu,gpu] from 1.1.5 to 1.1.6 (#6157) 2024-06-27 21:13:02 -03:00
dependabot[bot]
a5df8f4e3c
Bump jinja2 from 3.1.2 to 3.1.4 (#6172) 2024-06-27 21:12:39 -03:00
dependabot[bot]
c6cec0588c
Update accelerate requirement from ==0.30.* to ==0.31.* (#6156) 2024-06-27 21:12:02 -03:00
oobabooga
2f71515cb0 Make dependabot target the dev branch 2024-06-27 17:08:59 -07:00
oobabooga
1da47f2ae6 Make dependabot target the dev branch 2024-06-27 17:07:04 -07:00
oobabooga
9dbcb1aeea Small fix to make transformers 4.42 functional 2024-06-27 17:05:29 -07:00
oobabooga
66090758df Bump transformers to 4.42 (for gemma support) 2024-06-27 11:26:02 -07:00
oobabooga
6915c5077a
Merge pull request #6166 from oobabooga/dev
Merge dev branch
2024-06-26 23:33:09 -03:00
oobabooga
8ec8bc0b85 UI: handle another edge case while streaming lists 2024-06-26 18:40:43 -07:00
oobabooga
0e138e4be1 Merge remote-tracking branch 'refs/remotes/origin/dev' into dev 2024-06-26 18:30:08 -07:00
mefich
a85749dcbe
Update models_settings.py: add default alpha_value, add proper compress_pos_emb for newer GGUFs (#6111) 2024-06-26 22:17:56 -03:00
oobabooga
5fe532a5ce UI: remove DRY info text
It was visible for loaders without DRY.
2024-06-26 15:33:11 -07:00
oobabooga
b1187fc9a5 UI: prevent flickering while streaming lists / bullet points 2024-06-25 19:19:45 -07:00
oobabooga
3691451d00
Add back the "Rename chat" feature (#6161) 2024-06-25 22:28:58 -03:00
oobabooga
53fbd2f245 Add TensorRT-LLM to the README 2024-06-25 14:45:37 -07:00
oobabooga
ac3f92d36a UI: store chat history in the browser 2024-06-25 14:18:07 -07:00
oobabooga
46ca15cb79 Minor bug fixes after e7e1f5901e 2024-06-25 11:49:33 -07:00
oobabooga
83534798b2 UI: move "Character" dropdown to the main Chat tab 2024-06-25 11:25:57 -07:00
oobabooga
279cba607f UI: don't show an animation when updating the "past chats" menu 2024-06-25 11:10:17 -07:00
oobabooga
3290edfad9 Bug fix: force chat history to be loaded on launch 2024-06-25 11:06:05 -07:00
oobabooga
e7e1f5901e
Prompts in the "past chats" menu (#6160) 2024-06-25 15:01:43 -03:00
oobabooga
602b455507 Bump llama-cpp-python to 0.2.79 2024-06-24 20:26:38 -07:00
oobabooga
a43c210617
Improved past chats menu (#6158) 2024-06-25 00:07:22 -03:00
oobabooga
96ba53d916 Handle another fix after 57119c1b30 2024-06-24 15:51:12 -07:00
oobabooga
7db8b3b532 Bump ExLlamaV2 to 0.1.6 2024-06-24 05:38:11 -07:00
oobabooga
35f32d08bc GitHub: Increase the stalebot time to 6 months 2024-06-23 22:34:18 -07:00
oobabooga
564a3e1553 Remove the awkward "Tab" keyboard shortcut 2024-06-23 22:31:07 -07:00
oobabooga
577a8cd3ee
Add TensorRT-LLM support (#5715) 2024-06-24 02:30:03 -03:00
oobabooga
536f8d58d4 Do not expose alpha_value to llama.cpp & rope_freq_base to transformers
To avoid confusion
2024-06-23 22:09:24 -07:00
oobabooga
b48ab482f8 Remove obsolete "gptq_for_llama_info" message 2024-06-23 22:05:19 -07:00
oobabooga
5e8dc56f8a Fix after previous commit 2024-06-23 21:58:28 -07:00
Louis Del Valle
57119c1b30
Update block_requests.py to resolve unexpected type error (500 error) (#5976) 2024-06-24 01:56:51 -03:00
oobabooga
125bb7b03b Revert "Bump llama-cpp-python to 0.2.78"
This reverts commit b6eaf7923e.
2024-06-23 19:54:28 -07:00
CharlesCNorton
5993904acf
Fix several typos in the codebase (#6151) 2024-06-22 21:40:25 -03:00
GodEmperor785
2c5a9eb597
Change limits of RoPE scaling sliders in UI (#6142) 2024-06-19 21:42:17 -03:00
oobabooga
5904142777 Merge remote-tracking branch 'refs/remotes/origin/dev' into dev 2024-06-19 17:41:09 -07:00
oobabooga
b10d735176 Minor CSS linting 2024-06-19 17:40:33 -07:00
Guanghua Lu
229d89ccfb
Make logs more readable, no more \u7f16\u7801 (#6127) 2024-06-15 23:00:13 -03:00
oobabooga
fd7c3c5bb0 Don't git pull on installation (to make past releases installable) 2024-06-15 06:38:05 -07:00
oobabooga
b6eaf7923e Bump llama-cpp-python to 0.2.78 2024-06-14 21:22:09 -07:00
oobabooga
9420973b62
Downgrade PyTorch to 2.2.2 (#6124) 2024-06-14 16:42:03 -03:00
Forkoz
1576227f16
Fix GGUFs with no BOS token present, mainly qwen2 models. (#6119)
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2024-06-14 13:51:01 -03:00
dependabot[bot]
fdd8fab9cf
Bump hqq from 0.1.7.post2 to 0.1.7.post3 (#6090) 2024-06-14 13:46:35 -03:00
oobabooga
10601850d9 Fix after previous commit 2024-06-13 19:54:12 -07:00
oobabooga
0f3a423de1 Alternative solution to "get next logits" deadlock (#6106) 2024-06-13 19:34:16 -07:00
oobabooga
9aef01551d Revert "Use reentrant generation lock (#6107)"
This reverts commit b675151f25.
2024-06-13 17:53:07 -07:00
oobabooga
8930bfc5f4
Bump PyTorch, ExLlamaV2, flash-attention (#6122) 2024-06-13 20:38:31 -03:00
oobabooga
386500aa37 Avoid unnecessary calls UI -> backend, to make it faster 2024-06-12 20:52:42 -07:00
oobabooga
4820ae9aef
Merge pull request #6118 from oobabooga/dev
Merge dev branch
2024-06-13 00:38:03 -03:00
Forkoz
1d79aa67cf
Fix flash-attn UI parameter to actually store true. (#6076) 2024-06-13 00:34:54 -03:00