1380 Commits

Author	SHA1	Message	Date
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