3936 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
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
Belladore	3abafee696	DRY sampler improvements (#6053)	2024-06-12 23:39:11 -03:00
theo77186	b675151f25	Use reentrant generation lock (#6107)	2024-06-12 23:25:05 -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