17 Commits

Author	SHA1	Message	Date
somebody	111028642e	Fix tokenizer fallback for llama	2023-05-01 19:42:52 -05:00
onesome	9579298df7	Better fallback	2023-04-25 22:28:07 -05:00
somebody	4dcf570407	Fix legacy model loading	2023-04-15 12:57:35 -05:00
somebody	9d70646e4d	Lazyload: Safetensors	2023-04-02 15:40:34 -05:00
somebody	ffe85ce8a1	Modeling: Fix logits processors (probs, biasing, lua)	2023-03-17 16:56:47 -05:00
somebody	8d0bc404a5	Model: More Jax import fixes and formatting	2023-03-17 15:36:44 -05:00
somebody	b93c339145	Model: Lazyload backends	2023-03-13 20:29:29 -05:00
somebody	bf8b60ac2d	Model: Add GenericTokenizer ... Because Hugging Face doesnt have a consistant API across their own libraries	2023-03-13 17:36:58 -05:00
somebody	cd8ccf0a5e	Modeling: Add seed parameter to raw_generate ... Yahooo, decoupling from koboldai_vars. This makes the generation test pass in `test_generation.py`, and makes full determinism outside of core_generate work.	2023-03-12 21:49:10 -05:00
somebody	8c8bdfaf6a	Model: Fix assorted bugs ... and ignore warnings in pytest	2023-03-10 20:00:39 -06:00
somebody	52095054a3	Model: Reformat and clean up	2023-03-10 20:00:39 -06:00
somebody	fb0b2f0467	Model: Ditch awful current_model hack ... thanks to whjms for spotting that this could be zapped	2023-03-10 20:00:38 -06:00
somebody	3b05359e4b	Model: Refuse to serve certain models over the API	2023-03-07 16:54:08 -06:00
somebody	5d9bd96ad8	Model: Fix API support	2023-03-04 21:15:12 -06:00
somebody	70cddc46e2	Model: Small cleanup	2023-03-04 19:02:10 -06:00
somebody	27b7635c95	Model: Fix TPU	2023-03-04 19:02:00 -06:00
somebody	54cecd4d5d	Model: And another refactor	2023-03-01 19:16:35 -06:00