4093 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
oobabooga	e6eda6a3bb	Merge pull request #6645 from oobabooga/dev ... Merge dev branch v2.2	2025-01-09 18:46:28 -03:00
oobabooga	f3c0f964a2	Lint	2025-01-09 13:18:23 -08:00
oobabooga	0e94d7075e	UI: minor style fix on Windows	2025-01-09 13:12:30 -08:00
oobabooga	3020f2e5ec	UI: improve the info message about --tensorcores	2025-01-09 12:44:03 -08:00
oobabooga	c08d87b78d	Make the huggingface loader more readable	2025-01-09 12:23:38 -08:00
oobabooga	03b4067f31	Installer: ask 1 question for NVIDIA users instead of 2	2025-01-09 12:03:49 -08:00
BPplays	619265b32c	add ipv6 support to the API (#6559)	2025-01-09 10:23:44 -03:00
oobabooga	5c89068168	UI: add an info message for the new Static KV cache option	2025-01-08 17:36:30 -08:00
oobabooga	4ffc9ffc7a	UI: fix a list style	2025-01-08 17:24:38 -08:00
oobabooga	e6796c3859	Bump llama-cpp-python to 0.3.6, add macOS 14 and 15 wheels	2025-01-08 17:24:21 -08:00
nclok1405	b9e2ded6d4	Added UnicodeDecodeError workaround for modules/llamacpp_model.py (#6040) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2025-01-08 21:17:31 -03:00
oobabooga	91a8a87887	Remove obsolete code	2025-01-08 15:07:21 -08:00
oobabooga	ad118056b8	Update README	2025-01-08 14:29:46 -08:00
oobabooga	7157257c3f	Remove the AutoGPTQ loader (#6641)	2025-01-08 19:28:56 -03:00
Jack Cloudman	d3adcbf64b	Add --exclude-pattern flag to download-model.py script (#6542)	2025-01-08 17:30:21 -03:00
dependabot[bot]	1f86722977	Update safetensors requirement from ==0.4.* to ==0.5.* (#6634)	2025-01-08 16:56:55 -03:00
FP HAM	03a0f236a4	Training_PRO fix: add if 'quantization_config' in shared.model.config.to_dict()	2025-01-08 16:54:09 -03:00
oobabooga	c0f600c887	Add a --torch-compile flag for transformers	2025-01-05 05:47:00 -08:00
oobabooga	11af199aff	Add a "Static KV cache" option for transformers	2025-01-04 17:52:57 -08:00
oobabooga	3967520e71	Connect XTC, DRY, smoothing_factor, and dynatemp to ExLlamaV2 loader (non-HF)	2025-01-04 16:25:06 -08:00
oobabooga	d56b500568	UI: add padding to file saving dialog	2025-01-04 16:22:40 -08:00
oobabooga	049297fa66	UI: reduce the size of CSS sent to the UI during streaming	2025-01-04 14:09:36 -08:00
oobabooga	0e673a7a42	UI: reduce the size of HTML sent to the UI during streaming	2025-01-04 11:40:24 -08:00
mamei16	9f24885bd2	Sane handling of markdown lists (#6626)	2025-01-04 15:41:31 -03:00
oobabooga	3815f46838	UI: minor style improvements to chat tab	2025-01-03 04:35:29 -08:00
oobabooga	e2702200e1	UI: fix the font size of lists in chat mode	2025-01-02 19:26:50 -08:00
oobabooga	4b3e1b3757	UI: add a "Search chats" input field	2025-01-02 18:46:40 -08:00
oobabooga	b8fc9010fa	UI: fix orjson.JSONDecodeError error on page reload	2025-01-02 16:57:04 -08:00
oobabooga	973255cb0b	UI: fix codeblocks overflowing on mobile	2025-01-02 16:48:49 -08:00
oobabooga	75f1b5ccde	UI: add a "Branch chat" button	2025-01-02 16:24:18 -08:00
Petr Korolev	13c033c745	Fix CUDA error on MPS backend during API request (#6572) ... --------- Co-authored-by: oobabooga <oobabooga4@gmail.com>	2025-01-02 00:06:11 -03:00
oobabooga	979e1f1bd6	Fix a bug after 9163951f3aa65956ffcc7518d4a9c6ccca353b0b	2025-01-01 17:57:09 -08:00
oobabooga	f011787a83	UI: make codeblocks scroll horizontally on overflow	2025-01-01 17:55:18 -08:00
oobabooga	9163951f3a	UI: reduce the CPU usage during text streaming	2025-01-01 17:49:57 -08:00
oobabooga	725639118a	UI: Use a tab length of 2 for lists (rather than 4)	2025-01-01 13:53:50 -08:00
oobabooga	7b88724711	Make responses start faster by removing unnecessary cleanup calls (#6625)	2025-01-01 18:33:38 -03:00
oobabooga	88a6331abf	Merge pull request #6623 from oobabooga/dev ... Merge dev branch v2.1	2024-12-31 20:47:48 -03:00
oobabooga	64853f8509	Reapply a necessary change that I removed from #6599 (thanks @mamei16!)	2024-12-31 14:43:22 -08:00
mamei16	e953af85cd	Fix newlines in the markdown renderer (#6599) ... --------- Co-authored-by: oobabooga <oobabooga4@gmail.com>	2024-12-31 01:04:02 -03:00
dependabot[bot]	d24b83132b	Bump jinja2 from 3.1.4 to 3.1.5 (#6601)	2024-12-30 09:35:20 -03:00
mamei16	cca4ac56fa	Fix interface loading with dark theme even when 'dark_theme' is set to false (#6614)	2024-12-30 09:34:19 -03:00
oobabooga	292cd489e9	Bump ExLlamaV2 to 0.2.7	2024-12-30 04:31:10 -08:00
oobabooga	4ce9d13dbe	Preset cleanup (#6619)	2024-12-29 12:25:26 -03:00
oobabooga	39a5c9a49c	UI organization (#6618)	2024-12-29 11:16:17 -03:00
oobabooga	0490ee620a	UI: increase the threshold for a <li> to be considered long (some more)	2024-12-19 16:51:34 -08:00
oobabooga	ee3a533e5c	UI: improve the message width in instruct mode	2024-12-19 16:11:29 -08:00
oobabooga	89888bef56	UI: increase the threshold for a <li> to be considered long	2024-12-19 14:38:36 -08:00
oobabooga	2acec386fc	UI: improve the streaming cursor	2024-12-19 14:08:56 -08:00
oobabooga	e2fb86e5df	UI: further improve the style of lists and headings	2024-12-19 13:59:24 -08:00
oobabooga	c8ddb86c22	UI: improve some light mode colors	2024-12-19 12:24:04 -08:00