4988 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
oobabooga	005fcf3f98	Formatting	2025-09-17 21:58:37 -07:00
oobabooga	e4412f0634	Slightly more robust syntax highlighting	2025-09-17 21:57:17 -07:00
stevenxdavis	dd6d2223a5	Changing transformers_loader.py to Match User Expectations for --bf16 and Flash Attention 2 (#7217)	2025-09-17 16:39:04 -03:00
oobabooga	9e9ab39892	Make exllamav3_hf and exllamav2_hf functional again	2025-09-17 12:29:22 -07:00
oobabooga	9c0a833a0a	Revert "Update bitsandbytes requirement in /requirements/full (#7193)" ... This reverts commit fe15b67160.	2025-09-17 11:58:54 -07:00
oobabooga	8087a57fd8	Bump transformers to 4.56	2025-09-17 08:19:18 -07:00
dependabot[bot]	7131a478b9	Update safetensors requirement in /requirements/full (#7192)	2025-09-17 12:18:13 -03:00
dependabot[bot]	fe15b67160	Update bitsandbytes requirement in /requirements/full (#7193)	2025-09-17 12:17:58 -03:00
dependabot[bot]	8f731a566c	Update peft requirement from ==0.16.* to ==0.17.* in /requirements/full (#7172)	2025-09-17 12:17:16 -03:00
oobabooga	483927a5be	Update llama.cpp	2025-09-17 05:09:12 -07:00
oobabooga	557b78d31e	Update llama.cpp	2025-09-03 16:50:03 -07:00
oobabooga	ba62783b72	UI: Don't use $ $ for LaTeX, only $$ $$	2025-09-02 14:22:22 -07:00
oobabooga	f3829b268a	llama.cpp: Always pass --flash-attn on	2025-09-02 12:12:17 -07:00
oobabooga	2395c647d4	Fix the instruct message height on mobile	2025-09-02 12:11:15 -07:00
oobabooga	c6ea67bbdb	Lint	2025-09-02 10:22:03 -07:00
oobabooga	00ed878b05	Slightly more robust model loading	2025-09-02 10:16:26 -07:00
oobabooga	d843afcf66	Update llama.cpp	2025-09-02 05:43:33 -07:00
oobabooga	00ebb295d3	Update llama.cpp	2025-08-31 16:27:23 -07:00
oobabooga	387e249dec	Change an info message	2025-08-31 16:27:10 -07:00
oobabooga	8028d88541	Lint	2025-08-30 21:29:20 -07:00
oobabooga	13876a1ee8	llama.cpp: Remove the --flash-attn flag (it's always on now)	2025-08-30 20:28:26 -07:00
oobabooga	7b80e9a2ad	Update llama.cpp	2025-08-30 20:22:11 -07:00
oobabooga	5631d4e3d6	Minor change after 21d790f87e	2025-08-30 15:34:49 -07:00
oobabooga	5920ad8834	UI: Give streaming instruct messages more vertical space	2025-08-30 15:22:50 -07:00
oobabooga	21d790f87e	Optimize LaTeX rendering during streaming for long replies	2025-08-30 14:52:22 -07:00
oobabooga	3a3e247f3c	Even better way to handle continue for thinking blocks	2025-08-30 12:36:35 -07:00
oobabooga	cf1aad2a68	Fix "continue" for Byte-OSS for partial thinking blocks	2025-08-30 12:16:45 -07:00
oobabooga	96136ea760	Fix LaTeX rendering for equations with asterisks	2025-08-30 10:13:32 -07:00
oobabooga	a3eb67e466	Fix the UI failing to launch if the Notebook prompt is too long	2025-08-30 08:42:26 -07:00
oobabooga	08f90f4b64	Lint	2025-08-29 14:09:04 -07:00
oobabooga	07a2e226c1	UI: Minor font color fixes in instruct mode	2025-08-29 14:08:38 -07:00
oobabooga	a2b37adb26	UI: Preload the correct fonts for chat mode	2025-08-29 09:25:44 -07:00
oobabooga	084675cf75	UI: Improve thinking blocks in chat-instruct mode	2025-08-29 09:11:10 -07:00
oobabooga	d78b7d0fad	Lint	2025-08-28 20:22:07 -07:00
oobabooga	fc2eb48664	Style fixes after 73442a2b6d	2025-08-28 20:21:55 -07:00
oobabooga	2720955478	Fix a bug after d9eec31886	2025-08-28 19:48:16 -07:00
oobabooga	d9eec31886	UI: Suppress "Attempted to select a non-interactive or hidden tab" warnings	2025-08-28 17:46:29 -07:00
oobabooga	cb8780a4ce	Safer check for is_multimodal when loading models ... Avoids unrelated multimodal error when a model fails to load due to lack of memory.	2025-08-28 11:13:19 -07:00
oobabooga	cfc83745ec	UI: Improve right sidebar borders in light mode	2025-08-28 08:34:48 -07:00
oobabooga	a336a8bbeb	UI: Fix italic and quote color in headings	2025-08-28 08:26:40 -07:00
oobabooga	ba6041251d	UI: Minor change	2025-08-28 06:20:00 -07:00
oobabooga	a92758a144	llama.cpp: Fix obtaining the maximum sequence length for GPT-OSS	2025-08-27 16:15:40 -07:00
oobabooga	030ba7bfeb	UI: Mention that Seed-OSS uses enable_thinking	2025-08-27 07:44:35 -07:00
oobabooga	0b4518e61c	"Text generation web UI" -> "Text Generation Web UI"	2025-08-27 05:53:09 -07:00
oobabooga	73442a2b6d	UI: Better handle the chat input position with CSS ... This also solves scrolling issues with the main chat content when the height of the textarea increases.	2025-08-27 05:43:13 -07:00
oobabooga	8042f76399	Make portable installs functional with Python 3.13	2025-08-27 05:37:01 -07:00
oobabooga	ccc8a2229d	Revert "UI: Preserve chat scroll position on textarea resize" ... This reverts commit 750adf793d.	2025-08-26 13:59:54 -07:00
oobabooga	750adf793d	UI: Preserve chat scroll position on textarea resize	2025-08-26 12:19:23 -07:00
oobabooga	02ca96fa44	Multiple fixes	2025-08-25 22:17:22 -07:00
oobabooga	6a7166fffa	Add support for the Seed-OSS template	2025-08-25 19:46:48 -07:00