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
|
f32d26240d
|
UI: Fix the chat "stop" event
|
2024-07-26 23:03:05 -07:00 |
|
oobabooga
|
b80d5906c2
|
UI: fix saving characters
|
2024-07-25 15:09:31 -07:00 |
|
oobabooga
|
42e80108f5
|
UI: clear the markdown LRU cache when using the default/notebook tabs
|
2024-07-25 08:01:42 -07:00 |
|
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
|
e637b702ff
|
UI: make text between quotes colored in chat mode
|
2024-07-23 21:30:32 -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
|
f18c947a86
|
Update the tensorcores description
|
2024-07-22 18:06:41 -07:00 |
|
oobabooga
|
aa809e420e
|
Bump llama-cpp-python to 0.2.83, add back tensorcore wheels
Also add back the progress bar patch
|
2024-07-22 18:05:11 -07:00 |
|
oobabooga
|
11bbf71aa5
|
Bump back llama-cpp-python (#6257)
|
2024-07-22 16:19:41 -03:00 |
|
oobabooga
|
0f53a736c1
|
Revert the llama-cpp-python update
|
2024-07-22 12:02:25 -07:00 |
|
oobabooga
|
a687f950ba
|
Remove the tensorcores llama.cpp wheels
They are not faster than the default wheels anymore and they use a lot of space.
|
2024-07-22 11:54:35 -07:00 |
|
oobabooga
|
017d2332ea
|
Remove no longer necessary llama-cpp-python patch
|
2024-07-22 11:50:36 -07:00 |
|
oobabooga
|
f2d802e707
|
UI: make Default/Notebook contents persist on page reload
|
2024-07-22 11:07:10 -07:00 |
|
oobabooga
|
8768b69a2d
|
Lint
|
2024-07-21 22:08:14 -07:00 |
|
oobabooga
|
79e8dbe45f
|
UI: minor optimization
|
2024-07-21 22:06:49 -07:00 |
|
oobabooga
|
7ef2414357
|
UI: Make the file saving dialogs more robust
|
2024-07-21 15:38:20 -07:00 |
|
oobabooga
|
423372d6e7
|
Organize ui_file_saving.py
|
2024-07-21 13:23:18 -07:00 |
|
oobabooga
|
17df2d7bdf
|
UI: don't export the instruction template on "Save UI defaults to settings.yaml"
|
2024-07-21 10:45:01 -07:00 |
|
oobabooga
|
d05846eae5
|
UI: refresh the pfp cache on handle_your_picture_change
|
2024-07-21 10:17:22 -07:00 |
|
oobabooga
|
e9d4bff7d0
|
Update the --tensor_split description
|
2024-07-20 22:04:48 -07:00 |
|
oobabooga
|
916d1d8283
|
UI: improve the style of code blocks in light theme
|
2024-07-20 20:32:57 -07:00 |
|
oobabooga
|
564d8c8c0d
|
Make alpha_value a float number
|
2024-07-20 20:02:54 -07:00 |
|
oobabooga
|
79c4d3da3d
|
Optimize the UI (#6251)
|
2024-07-21 00:01:42 -03:00 |
|
Alberto Cano
|
a14c510afb
|
Customize the subpath for gradio, use with reverse proxy (#5106)
|
2024-07-20 19:10:39 -03:00 |
|
Vhallo
|
a9a6d72d8c
|
Use gr.Number for RoPE scaling parameters (#6233)
---------
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
|
2024-07-20 18:57:09 -03:00 |
|
oobabooga
|
aa7c14a463
|
Use chat-instruct mode by default
|
2024-07-19 21:43:52 -07:00 |
|
InvectorGator
|
4148a9201f
|
Fix for MacOS users encountering model load errors (#6227)
---------
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
Co-authored-by: Invectorgator <Kudzu12gaming@outlook.com>
|
2024-07-13 00:04:19 -03:00 |
|
oobabooga
|
e436d69e2b
|
Add --no_xformers and --no_sdpa flags for ExllamaV2
|
2024-07-11 15:47:37 -07:00 |
|
oobabooga
|
512b311137
|
Improve the llama-cpp-python exception messages
|
2024-07-11 13:00:29 -07:00 |
|
oobabooga
|
f957b17d18
|
UI: update an obsolete message
|
2024-07-10 06:01:36 -07:00 |
|
oobabooga
|
c176244327
|
UI: Move cache_8bit/cache_4bit further up
|
2024-07-05 12:16:21 -07:00 |
|
oobabooga
|
aa653e3b5a
|
Prevent llama.cpp from being monkey patched more than once (closes #6201)
|
2024-07-05 03:34:15 -07:00 |
|
oobabooga
|
a210e61df1
|
UI: Fix broken chat histories not showing (closes #6196)
|
2024-07-04 20:31:25 -07:00 |
|
oobabooga
|
e79e7b90dc
|
UI: Move the cache_8bit and cache_4bit elements up
|
2024-07-04 20:21:28 -07:00 |
|
oobabooga
|
8b44d7b12a
|
Lint
|
2024-07-04 20:16:44 -07:00 |
|
oobabooga
|
a47de06088
|
Force only 1 llama-cpp-python version at a time for now
|
2024-07-04 19:43:34 -07:00 |
|
oobabooga
|
f243b4ca9c
|
Make llama-cpp-python not crash immediately
|
2024-07-04 19:16:00 -07:00 |
|
oobabooga
|
907137a13d
|
Automatically set bf16 & use_eager_attention for Gemma-2
|
2024-07-01 21:46:35 -07:00 |
|
GralchemOz
|
8a39f579d8
|
transformers: Add eager attention option to make Gemma-2 work properly (#6188)
|
2024-07-01 12:08:08 -03:00 |
|
oobabooga
|
ed01322763
|
Obtain the EOT token from the jinja template (attempt)
To use as a stopping string.
|
2024-06-30 15:09:22 -07:00 |
|
oobabooga
|
4ea260098f
|
llama.cpp: add 4-bit/8-bit kv cache options
|
2024-06-29 09:10:33 -07:00 |
|
oobabooga
|
220c1797fc
|
UI: do not show the "save character" button in the Chat tab
|
2024-06-28 22:11:31 -07:00 |
|
oobabooga
|
8803ae1845
|
UI: decrease the number of lines for "Command for chat-instruct mode"
|
2024-06-28 21:41:30 -07:00 |
|
oobabooga
|
5c6b9c610d
|
UI: allow the character dropdown to coexist in the Chat tab and the Parameters tab (#6177)
|
2024-06-29 01:20:27 -03:00 |
|
oobabooga
|
de69a62004
|
Revert "UI: move "Character" dropdown to the main Chat tab"
This reverts commit 83534798b2.
|
2024-06-28 15:38:11 -07:00 |
|
oobabooga
|
38d58764db
|
UI: remove unused gr.State variable from the Default tab
|
2024-06-28 15:17:44 -07:00 |
|
oobabooga
|
da196707cf
|
UI: improve the light theme a bit
|
2024-06-27 21:05:38 -07:00 |
|
oobabooga
|
9dbcb1aeea
|
Small fix to make transformers 4.42 functional
|
2024-06-27 17:05:29 -07:00 |
|
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
|
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
|
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
|
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 |
|
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 |
|
Guanghua Lu
|
229d89ccfb
|
Make logs more readable, no more \u7f16\u7801 (#6127)
|
2024-06-15 23:00:13 -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 |
|
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
|
386500aa37
|
Avoid unnecessary calls UI -> backend, to make it faster
|
2024-06-12 20:52:42 -07:00 |
|
Forkoz
|
1d79aa67cf
|
Fix flash-attn UI parameter to actually store true. (#6076)
|
2024-06-13 00:34:54 -03:00 |
|
Belladore
|
3abafee696
|
DRY sampler improvements (#6053)
|
2024-06-12 23:39:11 -03:00 |
|
oobabooga
|
a36fa73071
|
Lint
|
2024-06-12 19:00:21 -07:00 |
|
oobabooga
|
2d196ed2fe
|
Remove obsolete pre_layer parameter
|
2024-06-12 18:56:44 -07:00 |
|
Belladore
|
46174a2d33
|
Fix error when bos_token_id is None. (#6061)
|
2024-06-12 22:52:27 -03:00 |
|
Belladore
|
a363cdfca1
|
Fix missing bos token for some models (including Llama-3) (#6050)
|
2024-05-27 09:21:30 -03:00 |
|
oobabooga
|
8df68b05e9
|
Remove MinPLogitsWarper (it's now a transformers built-in)
|
2024-05-27 05:03:30 -07:00 |
|
oobabooga
|
4f1e96b9e3
|
Downloader: Add --model-dir argument, respect --model-dir in the UI
|
2024-05-23 20:42:46 -07:00 |
|
oobabooga
|
ad54d524f7
|
Revert "Fix stopping strings for llama-3 and phi (#6043)"
This reverts commit 5499bc9bc8.
|
2024-05-22 17:18:08 -07:00 |
|
oobabooga
|
5499bc9bc8
|
Fix stopping strings for llama-3 and phi (#6043)
|
2024-05-22 13:53:59 -03:00 |
|
oobabooga
|
9e189947d1
|
Minor fix after bd7cc4234d (thanks @belladoreai)
|
2024-05-21 10:37:30 -07:00 |
|
oobabooga
|
ae86292159
|
Fix getting Phi-3-small-128k-instruct logits
|
2024-05-21 10:35:00 -07:00 |
|
oobabooga
|
bd7cc4234d
|
Backend cleanup (#6025)
|
2024-05-21 13:32:02 -03:00 |
|
Philipp Emanuel Weidmann
|
852c943769
|
DRY: A modern repetition penalty that reliably prevents looping (#5677)
|
2024-05-19 23:53:47 -03:00 |
|
oobabooga
|
9f77ed1b98
|
--idle-timeout flag to unload the model if unused for N minutes (#6026)
|
2024-05-19 23:29:39 -03:00 |
|
altoiddealer
|
818b4e0354
|
Let grammar escape backslashes (#5865)
|
2024-05-19 20:26:09 -03:00 |
|
Tisjwlf
|
907702c204
|
Fix gguf multipart file loading (#5857)
|
2024-05-19 20:22:09 -03:00 |
|
A0nameless0man
|
5cb59707f3
|
fix: grammar not support utf-8 (#5900)
|
2024-05-19 20:10:39 -03:00 |
|