Awni Hannun b8a348c1b8 Switch to fast RMS/LN Norm (#603) ...

* use nn.RMSNorm, use sdpa, cleanup

* bump mlx versions

* minor update

* use fast layer norm

* version bump

* update requirement for whisper

* update requirement for gguf

2024-03-23 07:13:51 -07:00

..

assets

Add large v3

2023-12-12 17:26:52 +01:00

__init__.py

Add llms subdir + update README (#145)

2023-12-20 10:22:25 -08:00

audio.py

Add large v3

2023-12-12 17:26:52 +01:00

decoding.py

work with tuple shape (#393)

2024-02-01 13:03:47 -08:00

load_models.py

Added lora support for Phi-2 (#302)

2024-01-12 13:45:30 -08:00

timing.py

[Whisper] Add word timestamps and confidence scores (#201)

2024-01-07 10:01:29 -08:00

tokenizer.py

Add large v3

2023-12-12 17:26:52 +01:00

torch_whisper.py

Add large v3

2023-12-12 17:26:52 +01:00

transcribe.py

[Lora] Fix generate (#282)

2024-01-10 16:13:06 -08:00

whisper.py

Switch to fast RMS/LN Norm (#603)

2024-03-23 07:13:51 -07:00