Commit Graph

3962 Commits

Author SHA1 Message Date
oobabooga
e926c03b3d Add a --tokenizer-dir command-line flag for llamacpp_HF 2024-08-06 19:41:18 -07:00
oobabooga
f106e780ba downloader: use 1 session for all files for better speed 2024-08-06 19:41:12 -07:00
oobabooga
608545d282 Bump llama-cpp-python to 0.2.85 2024-07-31 18:44:46 -07:00
oobabooga
30b4d8c8b2 Fix Llama 3.1 template including lengthy "tools" headers 2024-07-29 11:52:17 -07:00
oobabooga
f4d95f33b8 downloader: better progress bar 2024-07-28 22:21:56 -07:00
oobabooga
9dcff21da9 Remove unnecessary shared.previous_model_name variable 2024-07-28 18:35:11 -07:00
oobabooga
addcb52c56 Make --idle-timeout work for API requests 2024-07-28 18:31:40 -07:00
oobabooga
514fb2e451 Fix UI error caused by --idle-timeout 2024-07-28 18:30:06 -07:00
oobabooga
3aa646c1d0 UI: improve the style of headers in chat messages 2024-07-28 15:26:15 -07:00
oobabooga
92ab3a9a6a Bump llama-cpp-python to 0.2.84 2024-07-28 15:13:06 -07:00
oobabooga
5223c009fe Minor change after previous commit 2024-07-27 23:13:34 -07:00
oobabooga
7050bb880e UI: make n_ctx/max_seq_len/truncation_length numbers rather than sliders 2024-07-27 23:11:53 -07:00
Harry
078e8c8969
Make compress_pos_emb float (#6276) 2024-07-28 03:03:19 -03:00
oobabooga
ffc713f72b UI: fix multiline LaTeX equations 2024-07-27 15:36:10 -07:00
oobabooga
493f8c3242 UI: remove animation after clicking on "Stop" in the Chat tab 2024-07-27 15:22:34 -07:00
oobabooga
e4d411b841 UI: fix rendering LaTeX enclosed between \[ and \] 2024-07-27 15:21:44 -07:00
oobabooga
6bab4c2faa UI: add back single $ for equations 2024-07-26 23:03:53 -07:00
oobabooga
f32d26240d UI: Fix the chat "stop" event 2024-07-26 23:03:05 -07:00
oobabooga
9e82f8c394 UI: Fix chat sometimes not scrolling down after sending a message 2024-07-26 22:35:30 -07:00
oobabooga
c5814db173 UI: fix double quotes in instruct mode 2024-07-25 20:22:07 -07:00
oobabooga
b80d5906c2 UI: fix saving characters 2024-07-25 15:09:31 -07:00
oobabooga
e4624fbc68
Merge branch 'main' into dev 2024-07-25 12:03:45 -03:00
oobabooga
42e80108f5 UI: clear the markdown LRU cache when using the default/notebook tabs 2024-07-25 08:01:42 -07:00
oobabooga
a34273755b Revert "Updater: don't reinstall requirements if no updates after git pull"
This reverts commit ac30e7fe9c.
2024-07-25 07:34:01 -07:00
oobabooga
d581334a41 Don't install AutoAWQ on CUDA 11.8 2024-07-25 05:38:52 -07:00
oobabooga
14584fda36 UI: don't change the color of italics in instruct mode 2024-07-24 20:55:18 -07:00
oobabooga
b85ae6bc96 Fix after previous commit 2024-07-24 19:10:17 -07:00
oobabooga
b6830bcdae Merge remote-tracking branch 'refs/remotes/origin/dev' into dev 2024-07-24 19:04:38 -07:00
oobabooga
ac30e7fe9c Updater: don't reinstall requirements if no updates after git pull 2024-07-24 19:03:34 -07:00
oobabooga
1f101ee3e5 UI: improve the quote colors 2024-07-24 18:56:54 -07:00
Luana
3170b6efc9
Fixes Linux shebangs (#6110) 2024-07-24 22:23:29 -03:00
oobabooga
7e2851e505 UI: fix "Command for chat-instruct mode" not appearing by default 2024-07-24 15:04:12 -07:00
oobabooga
947016d010 UI: make the markdown LRU cache infinite (for really long conversations) 2024-07-24 11:54:26 -07:00
oobabooga
3b2c23dfb5 Add AutoAWQ 0.2.6 wheels for PyTorch 2.2.2 2024-07-24 11:15:00 -07:00
oobabooga
8a5f110c14 Bump ExLlamaV2 to 0.1.8 2024-07-24 09:22:48 -07:00
oobabooga
e637b702ff UI: make text between quotes colored in chat mode 2024-07-23 21:30:32 -07:00
oobabooga
98ed6d3a66 Don't use flash attention on Google Colab 2024-07-23 19:50:56 -07:00
oobabooga
af839d20ac Remove the AutoAWQ requirement 2024-07-23 19:38:39 -07:00
oobabooga
9d5513fda0 Remove the AutoAWQ requirement 2024-07-23 19:38:04 -07:00
oobabooga
8b52b93e85 Make the Google Colab notebook functional again (attempt) 2024-07-23 19:35:00 -07:00
oobabooga
e777b73349 UI: prevent LaTeX from being rendered for inline "$" 2024-07-23 19:04:19 -07:00
oobabooga
1815877061 UI: fix the default character not loading correctly on startup 2024-07-23 18:48:10 -07:00
oobabooga
e6181e834a Remove AutoAWQ as a standalone loader
(it works better through transformers)
2024-07-23 15:31:17 -07:00
oobabooga
f66ab63d64 Bump transformers to 4.43 2024-07-23 14:06:34 -07:00
oobabooga
6b4d762120
Merge pull request #6261 from oobabooga/dev
Merge dev branch
2024-07-23 03:11:02 -03:00
oobabooga
95b3e98c36 UI: Fix code syntax highlighting 2024-07-22 23:08:48 -07:00
oobabooga
d1115f18b9
Merge pull request #6260 from oobabooga/dev
Merge dev branch
2024-07-23 02:30:35 -03:00
oobabooga
3ee682208c Revert "Bump hqq from 0.1.7.post3 to 0.1.8 (#6238)"
This reverts commit 1c3671699c.
2024-07-22 19:53:56 -07:00
oobabooga
5e7f4ee88a UI: simplify the interface load events 2024-07-22 19:11:55 -07:00
oobabooga
5c5e7264ec Update README 2024-07-22 18:20:01 -07:00