1545 commits

Author	SHA1	Message	Date
oobabooga	5ad080ff25	Attempt at making the llama-server streaming more efficient.	2025-04-18 18:04:49 -07:00
oobabooga	4fabd729c9	Fix the API without streaming or without 'sampler_priority' (closes #6851)	2025-04-18 17:25:22 -07:00
oobabooga	5135523429	Fix the new llama.cpp loader failing to unload models	2025-04-18 17:10:26 -07:00
oobabooga	caa6afc88b	Only show 'GENERATE_PARAMS=...' in the logits endpoint if use_logits is True	2025-04-18 09:57:57 -07:00
oobabooga	d00d713ace	Rename get_max_context_length to get_vocabulary_size in the new llama.cpp loader	2025-04-18 08:14:15 -07:00
oobabooga	c1cc65e82e	Lint	2025-04-18 08:06:51 -07:00
oobabooga	d68f0fbdf7	Remove obsolete references to llamacpp_HF	2025-04-18 07:46:04 -07:00
oobabooga	a0abf93425	Connect --rope-freq-base to the new llama.cpp loader	2025-04-18 06:53:51 -07:00
oobabooga	ef9910c767	Fix a bug after c6901aba9f	2025-04-18 06:51:28 -07:00
oobabooga	1c4a2c9a71	Make exllamav3 safer as well	2025-04-18 06:17:58 -07:00
oobabooga	c6901aba9f	Remove deprecation warning code	2025-04-18 06:05:47 -07:00
oobabooga	8144e1031e	Remove deprecated command-line flags	2025-04-18 06:02:28 -07:00
oobabooga	ae54d8faaa	New llama.cpp loader (#6846)	2025-04-18 09:59:37 -03:00
oobabooga	5c2f8d828e	Fix exllamav2 generating eos randomly after previous fix	2025-04-18 05:42:38 -07:00
oobabooga	2fc58ad935	Consider files with .pt extension in the new model menu function	2025-04-17 23:10:43 -07:00
Googolplexed	d78abe480b	Allow for model subfolder organization for GGUF files (#6686) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2025-04-18 02:53:59 -03:00
oobabooga	ce9e2d94b1	Revert "Attempt at solving the ExLlamaV2 issue" ... This reverts commit c9b3c9dfbf.	2025-04-17 22:03:21 -07:00
oobabooga	5dfab7d363	New attempt at solving the exl2 issue	2025-04-17 22:03:11 -07:00
oobabooga	c9b3c9dfbf	Attempt at solving the ExLlamaV2 issue	2025-04-17 21:45:15 -07:00
oobabooga	2c2d453c8c	Revert "Use ExLlamaV2 (instead of the HF one) for EXL2 models for now" ... This reverts commit 0ef1b8f8b4.	2025-04-17 21:31:32 -07:00
oobabooga	0ef1b8f8b4	Use ExLlamaV2 (instead of the HF one) for EXL2 models for now ... It doesn't seem to have the "OverflowError" bug	2025-04-17 05:47:40 -07:00
oobabooga	682c78ea42	Add back detection of GPTQ models (closes #6841)	2025-04-11 21:00:42 -07:00
oobabooga	4ed0da74a8	Remove the obsolete 'multimodal' extension	2025-04-09 20:09:48 -07:00
oobabooga	598568b1ed	Revert "UI: remove the streaming cursor" ... This reverts commit 6ea0206207.	2025-04-09 16:03:14 -07:00
oobabooga	297a406e05	UI: smoother chat streaming ... This removes the throttling associated to gr.Textbox that made words appears in chunks rather than one at a time	2025-04-09 16:02:37 -07:00
oobabooga	6ea0206207	UI: remove the streaming cursor	2025-04-09 14:59:34 -07:00
oobabooga	8b8d39ec4e	Add ExLlamaV3 support (#6832)	2025-04-09 00:07:08 -03:00
oobabooga	bf48ec8c44	Remove an unnecessary UI message	2025-04-07 17:43:41 -07:00
oobabooga	a5855c345c	Set context lengths to at most 8192 by default (to prevent out of memory errors) (#6835)	2025-04-07 21:42:33 -03:00
oobabooga	109de34e3b	Remove the old --model-menu flag	2025-03-31 09:24:03 -07:00
oobabooga	758c3f15a5	Lint	2025-03-14 20:04:43 -07:00
oobabooga	5bcd2d7ad0	Add the top N-sigma sampler (#6796)	2025-03-14 16:45:11 -03:00
oobabooga	26317a4c7e	Fix jinja2 error while loading c4ai-command-a-03-2025	2025-03-14 10:59:05 -07:00
Kelvie Wong	16fa9215c4	Fix OpenAI API with new param (show_after), closes #6747 (#6749) ... --------- Co-authored-by: oobabooga <oobabooga4@gmail.com>	2025-02-18 12:01:30 -03:00
oobabooga	dba17c40fc	Make transformers 4.49 functional	2025-02-17 17:31:11 -08:00
SamAcctX	f28f39792d	update deprecated deepspeed import for transformers 4.46+ (#6725)	2025-02-02 20:41:36 -03:00
oobabooga	c6f2c2fd7e	UI: style improvements	2025-02-02 15:34:03 -08:00
oobabooga	0360f54ae8	UI: add a "Show after" parameter (to use with DeepSeek </think>)	2025-02-02 15:30:09 -08:00
oobabooga	f01cc079b9	Lint	2025-01-29 14:00:59 -08:00
oobabooga	75ff3f3815	UI: Mention common context length values	2025-01-25 08:22:23 -08:00
FP HAM	71a551a622	Add strftime_now to JINJA to sattisfy LLAMA 3.1 and 3.2 (and granite) (#6692)	2025-01-24 11:37:20 -03:00
oobabooga	0485ff20e8	Workaround for convert_to_markdown bug	2025-01-23 06:21:40 -08:00
oobabooga	39799adc47	Add a helpful error message when llama.cpp fails to load the model	2025-01-21 12:49:12 -08:00
oobabooga	5e99dded4e	UI: add "Continue" and "Remove" buttons below the last chat message	2025-01-21 09:05:44 -08:00
oobabooga	0258a6f877	Fix the Google Colab notebook	2025-01-16 05:21:18 -08:00
oobabooga	1ef748fb20	Lint	2025-01-14 16:44:15 -08:00
oobabooga	f843cb475b	UI: update a help message	2025-01-14 08:12:51 -08:00
oobabooga	c832953ff7	UI: Activate auto_max_new_tokens by default	2025-01-14 05:59:55 -08:00
Underscore	53b838d6c5	HTML: Fix quote pair RegEx matching for all quote types (#6661)	2025-01-13 18:01:50 -03:00
oobabooga	c85e5e58d0	UI: move the new morphdom code to a .js file	2025-01-13 06:20:42 -08:00