ebolam 1a1b79a16d Change default for HF on non-breakmodel models to use GPU instead of CPU

2023-05-24 12:44:26 -04:00

..

inference_models

Change default for HF on non-breakmodel models to use GPU instead of CPU

2023-05-24 12:44:26 -04:00

inference_model.py

Moved model backends to separate folders

2023-05-18 20:14:33 -04:00

lazy_loader.py

Unban fix

2023-05-15 22:38:12 +02:00

logits_processors.py

Modeling: Fix logits processors (probs, biasing, lua)

2023-03-17 16:56:47 -05:00

patches.py

Model: And another refactor

2023-03-01 19:16:35 -06:00

post_token_hooks.py

Model: Respect model lazyload over kaivars

2023-03-10 20:00:39 -06:00

stoppers.py

Potential fix

2023-04-27 19:51:10 -05:00

test_generation.py

Model: More Jax import fixes and formatting

2023-03-17 15:36:44 -05:00

tokenizer.py

Fix tokenizer fallback for llama

2023-05-01 19:42:52 -05:00

warpers.py

Undo pretty code because I haven't cracked the jax enigma yet

2023-04-25 21:11:49 -05:00