somebody 91bb433b5f GenericTokenizer: Fall back to defined tokenizer ...

Shouldn't be relied on for model-agnostic code, but for loading
processes where you know the tokenizer class used it should be okie
dokie

2023-03-19 19:03:20 -05:00

..

api.py

Model: WIP horde and API tests

2023-03-13 14:11:06 -05:00

basic_api.py

Modeling: Add seed parameter to raw_generate

2023-03-12 21:49:10 -05:00

generic_hf_torch.py

GenericTokenizer: Fall back to defined tokenizer

2023-03-19 19:03:20 -05:00

hf_mtj.py

Model: More Jax import fixes and formatting

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

hf_torch.py

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

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

hf.py

Model: Fix assorted bugs

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

horde.py

Model: WIP horde and API tests

2023-03-13 14:11:06 -05:00

legacy_gpt2_hf.py

Model: Respect model lazyload over kaivars

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

openai.py

Modeling: Add seed parameter to raw_generate

2023-03-12 21:49:10 -05:00

rwkv.py

Model: More Jax import fixes and formatting

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