67 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
Ashwin Bharambe	0df57c4447	fix bad merge with injection shield?	2024-07-20 23:54:44 -07:00
Hardik Shah	2408bd81c8	easy script to create config	2024-07-20 23:51:46 -07:00
Ashwin Bharambe	7c9ed3e58e	update README a bit	2024-07-20 23:26:50 -07:00
Ashwin Bharambe	d73fed5cc3	cleanup for fp8 and requirements etc	2024-07-20 23:21:55 -07:00
Hardik Shah	2428701951	download inside model_name directory	2024-07-20 23:16:19 -07:00
Ashwin Bharambe	0746a0f62b	fp8 inference	2024-07-20 23:13:47 -07:00
Ashwin Bharambe	ad62e2e1f3	make inference server load checkpoints for fp8 inference ... - introduce quantization related args for inference config - also kill GeneratorArgs	2024-07-20 22:54:48 -07:00
Ashwin Bharambe	7d2c0b14b8	Changes from the main repo	2024-07-20 22:52:29 -07:00
Hardik Shah	9c9b834c0f	update prompt-shield to reflect latest changes in agentic	2024-07-19 18:12:09 -07:00
Hardik Shah	ce0804556b	update requirements for running standalone	2024-07-19 18:11:25 -07:00
Hardik Shah	2ed2881a21	fixed imports models.llama3. --> models.llama3_1.api.	2024-07-19 17:42:14 -07:00
Ashwin Bharambe	f94efcf2ee	kill older junk	2024-07-19 12:32:22 -07:00
Ashwin Bharambe	95781ec85d	Add toolchain from agentic system here	2024-07-19 12:30:35 -07:00
Ashwin Bharambe	f6b2b2fb39	cleanup	2024-07-11 10:04:56 -07:00
Raghotham Murthy	6d6c07b882	added more docs	2024-07-11 03:12:28 -07:00
Raghotham Murthy	8631d90f1e	added more docs	2024-07-11 03:11:45 -07:00
Raghotham Murthy	e657e71446	added more docs	2024-07-11 03:10:30 -07:00
Raghotham Murthy	ab44e9c862	added more docs	2024-07-11 03:09:45 -07:00
raghotham	62f2db8f62	saving the spec changes	2024-07-11 05:02:16 -04:00
Raghotham Murthy	0e4b9efedf	added more docs	2024-07-11 01:54:03 -07:00
Raghotham Murthy	9070d45629	added more docs	2024-07-11 01:48:13 -07:00
Raghotham Murthy	65556d0a1c	added more docs	2024-07-11 01:46:33 -07:00
Raghotham Murthy	b88f8ad616	added more docs	2024-07-11 01:38:04 -07:00
Raghotham Murthy	6778359493	added more docs	2024-07-11 01:36:02 -07:00
Raghotham Murthy	dad480ded7	added more docs	2024-07-11 01:33:24 -07:00
Raghotham Murthy	0eabaffc3f	added more docs	2024-07-11 01:32:24 -07:00
Raghotham Murthy	f431c18efc	added more docs	2024-07-11 01:32:17 -07:00
Raghotham Murthy	5704847d74	added more docs	2024-07-11 01:26:42 -07:00
Raghotham Murthy	bf18ba3940	added more docs	2024-07-11 01:26:34 -07:00
Raghotham Murthy	067ec4ce50	added memory_bank endpoint	2024-07-11 00:14:28 -07:00
Ashwin Bharambe	86c2993296	small rename	2024-07-11 00:07:19 -07:00
Ashwin Bharambe	631328f556	added DPO	2024-07-11 00:01:58 -07:00
Ashwin Bharambe	7cade3acc3	fixes	2024-07-10 23:33:57 -07:00
Ashwin Bharambe	ee86f2c75f	memory banks	2024-07-10 23:28:16 -07:00
Raghotham Murthy	6fb69efbe5	Added batch inference	2024-07-10 23:25:23 -07:00
Raghotham Murthy	22d6093258	missed html/yaml	2024-07-10 23:01:00 -07:00
Raghotham Murthy	f63fff92ae	fix indentation	2024-07-10 23:00:12 -07:00
Raghotham Murthy	d9367054df	sdg improvements	2024-07-10 22:58:29 -07:00
Ashwin Bharambe	c1f6816d76	some finetuning changes	2024-07-10 22:09:13 -07:00
Raghotham Murthy	6ec7c47938	reward scoring model enum	2024-07-10 21:59:01 -07:00
Raghotham Murthy	ebb59aa35f	reward scoring	2024-07-10 21:56:16 -07:00
Ashwin Bharambe	69ecf55de2	finetuning	2024-07-10 20:47:05 -07:00
Ashwin Bharambe	956f07b04c	fixes to reward stuff	2024-07-10 19:22:33 -07:00
Raghotham Murthy	eb12bfbef0	add reward scoring and synthetic data gen	2024-07-10 15:42:56 -07:00
Ashwin Bharambe	beb2870750	initial client + server for agentic system	2024-07-09 22:17:36 -07:00
Ashwin Bharambe	13e1667e7a	add safety	2024-07-09 16:08:47 -07:00
Ashwin Bharambe	256f1d5991	agentic system stream changes	2024-07-09 15:08:54 -07:00
Ashwin Bharambe	97f9b18aca	more work on agent definitions	2024-07-09 13:53:09 -07:00
Ashwin Bharambe	6e4586ba7a	more definitions	2024-07-08 16:35:28 -07:00
Ashwin Bharambe	722d20c6de	making the API python based with a converter script	2024-07-08 15:01:05 -07:00