Anchen 8a178f8716 chore: enable tie_word_embeddings config for qwen2 (#544)

2024-03-07 06:11:35 -08:00

..

__init__.py

Mlx llm package (#301)

2024-01-12 10:25:56 -08:00

base.py

Mlx llm package (#301)

2024-01-12 10:25:56 -08:00

gemma.py

[mlx-lm] Add precompiled normalizations (#451)

2024-02-22 12:40:55 -08:00

layers.py

[mlx-lm] Add precompiled normalizations (#451)

2024-02-22 12:40:55 -08:00

llama.py

[mlx-lm] Add precompiled normalizations (#451)

2024-02-22 12:40:55 -08:00

mixtral.py

[mlx-lm] Add precompiled normalizations (#451)

2024-02-22 12:40:55 -08:00

olmo.py

[mlx-lm] Add precompiled normalizations (#451)

2024-02-22 12:40:55 -08:00

phi.py

[mlx-lm] Add precompiled normalizations (#451)

2024-02-22 12:40:55 -08:00

phixtral.py

[mlx-lm] Add precompiled normalizations (#451)

2024-02-22 12:40:55 -08:00

plamo.py

[mlx-lm] Add precompiled normalizations (#451)

2024-02-22 12:40:55 -08:00

qwen2.py

chore: enable tie_word_embeddings config for qwen2 (#544)

2024-03-07 06:11:35 -08:00

qwen.py

[mlx-lm] Add precompiled normalizations (#451)

2024-02-22 12:40:55 -08:00

stablelm.py

Add Starcoder 2 (#502)

2024-03-02 19:39:23 -08:00

starcoder2.py

Add tips on porting LLMs from HuggingFace (#523)

2024-03-05 17:43:15 -08:00