373 Commits

Author	SHA1	Message	Date
oobabooga	510a01ef46	Lint	2023-11-16 18:03:06 -08:00
oobabooga	a475aa7816	Improve API documentation	2023-11-15 18:39:08 -08:00
oobabooga	a85ce5f055	Add more info messages for truncation / instruction template	2023-11-15 16:20:31 -08:00
oobabooga	e6f44d6d19	Print context length / instruction template to terminal when loading models	2023-11-15 16:00:51 -08:00
oobabooga	be125e2708	Add /v1/internal/model/unload endpoint	2023-11-15 15:48:33 -08:00
oobabooga	52758f15da	Remove sentence-transformers requirement (for #1575)	2023-11-10 07:35:29 -08:00
oobabooga	c5be3f7acb	Make /v1/embeddings functional, add request/response types	2023-11-10 07:34:27 -08:00
oobabooga	0777b0d3c7	Add system_message parameter, document model (unused) parameter	2023-11-10 06:47:18 -08:00
oobabooga	4aabff3728	Remove old API, launch OpenAI API with --api	2023-11-10 06:39:08 -08:00
GuizzyQC	6a7cd01ebf	Fix bug with /internal/model/load (#4549) ... Update shared.model_name after loading model through API call	2023-11-10 00:16:38 -03:00
Ashley Kleynhans	372d712921	Fix deprecated API (#4539)	2023-11-09 14:51:50 -03:00
oobabooga	d86f1fd2c3	OpenAI API: stop streaming on client disconnect (closes #4521)	2023-11-09 06:37:32 -08:00
oobabooga	effb3aef42	Prevent deadlocks in OpenAI API with simultaneous requests	2023-11-08 20:55:39 -08:00
oobabooga	678fd73aef	Document /v1/internal/model/load and fix a bug	2023-11-08 17:41:12 -08:00
MrMojoR	1754a3761b	Include trust remote code usage in openai api's embedder (#4513)	2023-11-08 11:25:43 -03:00
hronoas	6c7aad11f3	openai extension: wrong frequency_penalty type (#4512)	2023-11-08 11:23:51 -03:00
oobabooga	881e8a6e70	Small bug fix in /v1/internal/model/load	2023-11-08 02:34:13 -03:00
oobabooga	050ff36bd6	Revert "Add a comment to /v1/models" ... This reverts commit 38b07493a0.	2023-11-07 21:09:47 -08:00
oobabooga	38b07493a0	Add a comment to /v1/models	2023-11-07 21:07:12 -08:00
oobabooga	2358706453	Add /v1/internal/model/load endpoint (tentative)	2023-11-07 20:58:06 -08:00
oobabooga	43c53a7820	Refactor the /v1/models endpoint	2023-11-07 19:59:27 -08:00
oobabooga	1b69694fe9	Add types to the encode/decode/token-count endpoints	2023-11-07 19:32:14 -08:00
oobabooga	f6ca9cfcdc	Add /v1/internal/model-info endpoint	2023-11-07 18:59:02 -08:00
oobabooga	6e2e0317af	Separate context and system message in instruction formats (#4499)	2023-11-07 20:02:58 -03:00
oobabooga	3fc505dc0f	Document unused parameters	2023-11-07 08:56:09 -08:00
oobabooga	3d59346871	Implement echo/suffix parameters	2023-11-07 08:43:45 -08:00
oobabooga	48c9c31440	Document the "preset" option in the API	2023-11-07 08:23:17 -08:00
oobabooga	79b3f5a546	Add /v1/internal/stop-generation to OpenAI API (#4498)	2023-11-07 00:10:42 -03:00
oobabooga	97c21e5667	Don't strip leading spaces in OpenAI API	2023-11-06 19:09:41 -08:00
oobabooga	4a45dc4041	Reorder the parameters in the FastAPI documentation	2023-11-06 09:55:36 -08:00
oobabooga	0ed6a17ed4	Update warning	2023-11-06 07:17:49 -08:00
oobabooga	0db81355bc	Reorder a parameter	2023-11-06 07:11:49 -08:00
oobabooga	b87c6213ae	Remove obsolete endpoint	2023-11-06 05:45:45 -08:00
oobabooga	28fd535f9c	Make chat API more robust	2023-11-06 05:22:01 -08:00
oobabooga	ec17a5d2b7	Make OpenAI API the default API (#4430)	2023-11-06 02:38:29 -03:00
俞航	84d957ba62	[Fix] fix openai embedding_model loading as str (#4147)	2023-11-05 20:42:45 -03:00
kabachuha	e18a0460d4	fix openai extension not working because of absent new defaults (#4477)	2023-11-04 16:12:51 -03:00
oobabooga	aa5d671579	Add temperature_last parameter (#4472)	2023-11-04 13:09:07 -03:00
oobabooga	7f9c1cbb30	Change min_p default to 0.0	2023-11-03 08:25:22 -07:00
kalomaze	367e5e6e43	Implement Min P as a sampler option in HF loaders (#4449)	2023-11-02 16:32:51 -03:00
Abhilash Majumder	778a010df8	Intel Gpu support initialization (#4340)	2023-10-26 23:39:51 -03:00
GuizzyQC	317e2c857e	sd_api_pictures: fix Gradio warning message regarding custom value (#4391)	2023-10-26 23:03:21 -03:00
tdrussell	72f6fc6923	Rename additive_repetition_penalty to presence_penalty, add frequency_penalty (#4376)	2023-10-25 12:10:28 -03:00
tdrussell	4440f87722	Add additive_repetition_penalty sampler setting. (#3627)	2023-10-23 02:28:07 -03:00
Jiashu Xu	c544f5cc51	Support LLaVA v1.5 7B (#4348)	2023-10-22 12:49:04 -03:00
FartyPants (FP HAM)	6a61158adf	Training PRO a month worth of updates (#4345)	2023-10-22 12:38:09 -03:00
oobabooga	1a34927314	Make API URLs more visible	2023-10-21 21:11:07 -07:00
Haotian Liu	32984ea2f0	Support LLaVA v1.5 (#4305)	2023-10-20 02:28:14 -03:00
missionfloyd	c0ffb77fd8	More silero languages (#3950)	2023-10-16 17:12:32 -03:00
hronoas	db7ecdd274	openai: fix empty models list on query present in url (#4139)	2023-10-16 17:02:47 -03:00