kingbri d759a15559 Model: Fix chunk size handling ...

Wrong class attribute name used for max_attention_size and fixes
declaration of the draft model's chunk_size.

Also expose the parameter to the end user in both config and model
load.

Signed-off-by: kingbri <bdashore3@proton.me>

2024-04-07 18:39:19 -04:00

..

grammar.py

Model: Prompt users to install extras if dependencies don't exist

2024-03-22 22:13:55 -04:00

model.py

Model: Fix chunk size handling

2024-04-07 18:39:19 -04:00

utils.py

Requirements: Update Exllamav2

2024-04-07 18:00:56 -04:00