Commit Graph

4041 Commits

Author SHA1 Message Date
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
FartyPants (FP HAM)
6ab477f375
training: Added ChatML-format.json format example (#5899) 2024-07-20 19:05:09 -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
dependabot[bot]
1c3671699c
Bump hqq from 0.1.7.post3 to 0.1.8 (#6238) 2024-07-20 18:20:26 -03:00
oobabooga
aa7c14a463 Use chat-instruct mode by default 2024-07-19 21:43:52 -07:00
oobabooga
0315122cf0
Merge pull request #6232 from oobabooga/dev
Merge dev branch
2024-07-13 14:52:34 -03:00
oobabooga
b19d239a60 Bump flash-attention to 2.6.1 2024-07-12 20:16:11 -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
d01c68f2a3
Merge pull request #6224 from oobabooga/dev
Merge dev branch
2024-07-11 20:42:46 -03:00
oobabooga
05676caf70 Update README 2024-07-11 16:25:52 -07:00
oobabooga
f5599656b4 Update README 2024-07-11 16:22:00 -07:00
oobabooga
d4eac58f2d Merge remote-tracking branch 'refs/remotes/origin/dev' into dev 2024-07-11 16:21:16 -07:00
oobabooga
a30ec2e7db Update README 2024-07-11 16:20:44 -07:00
dependabot[bot]
063d2047dd
Update accelerate requirement from ==0.31.* to ==0.32.* (#6217) 2024-07-11 19:56:42 -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
01e4721da7 Bump ExLlamaV2 to 0.1.7 2024-07-11 12:33:46 -07:00
oobabooga
fa075e41f4 Bump llama-cpp-python to 0.2.82 2024-07-10 06:03:24 -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
e813b322cf
Merge pull request #6203 from oobabooga/dev
Merge dev branch
2024-07-05 07:37:19 -03:00
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
3315d00651
Merge pull request #6200 from oobabooga/dev
Merge dev branch
2024-07-05 00:22:24 -03:00
oobabooga
e79e7b90dc UI: Move the cache_8bit and cache_4bit elements up 2024-07-04 20:21:28 -07:00
oobabooga
363efe54f4
Merge pull request #6199 from oobabooga/dev
Merge dev branch
2024-07-05 00:17:14 -03:00
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
f77cf159ba UI: fix a glitch when switching tabs with "show controls" unchecked 2024-07-02 20:57:03 -07:00
oobabooga
7e22eaa36c Bump llama-cpp-python to 0.2.81 2024-07-02 20:29:35 -07:00
oobabooga
907137a13d Automatically set bf16 & use_eager_attention for Gemma-2 2024-07-01 21:46:35 -07:00
TimStrauven
8074fba18d
Whisper stt overhaul js (#6194)
---------

Co-authored-by: RandoInternetPreson <aaronalai1@gmail.com>
2024-07-01 23:27:18 -03:00
GralchemOz
8a39f579d8
transformers: Add eager attention option to make Gemma-2 work properly (#6188) 2024-07-01 12:08:08 -03:00
oobabooga
19a56dd538 UI: Minor CSS improvement to chat mode 2024-06-30 21:09:54 -07:00
oobabooga
1ea3826333 UI: improve the chat area width on mobile devices 2024-06-30 17:08:23 -07:00
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
3e3f8637d6 Fix the AUTOMATIC1111 request in sd-api-pictures (closes #5993) 2024-06-29 11:43:57 -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
f62aad3d59 Merge remote-tracking branch 'refs/remotes/origin/dev' into dev 2024-06-28 21:42:03 -07:00
oobabooga
8803ae1845 UI: decrease the number of lines for "Command for chat-instruct mode" 2024-06-28 21:41:30 -07:00
mamei16
cc825dd1f4
Addressing Whisper STT issues (#5929) 2024-06-29 01:32:54 -03:00
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
04cb197ed6 Merge remote-tracking branch 'refs/remotes/origin/dev' into dev 2024-06-27 21:25:23 -07:00
oobabooga
da196707cf UI: improve the light theme a bit 2024-06-27 21:05:38 -07:00