mlx-examples/mlx_lm at d661440dbb8e1970fadad79c5061e786fe1c54ca - mlx-examples - Gitea for Geophysics

zhangyiss/mlx-examples

mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-10-29 01:18:08 +08:00

Files

History

Prince Canuma d661440dbb Add support for qwen2moe (#640 )

* add sparsemoe block and update decoder logic

* update file name to match HF

* update name

* Code formatting

* update gates calculation

* add support for Qwen2MoE.

* fix pytest

* code formatting and fix missing comma in utils

* Remove decoder sparse step.

Co-authored-by: bozheng-hit <dsoul0621@gmail.com>

* remove gate layer anti-quantisation

* remove unused argument

---------

Co-authored-by: bozheng-hit <dsoul0621@gmail.com>

2024-04-02 11:33:29 -07:00

..

Configurable LR schedulers (#604 )

2024-03-29 13:41:10 -07:00

Add support for qwen2moe (#640 )

2024-04-02 11:33:29 -07:00

Add support for qwen2moe (#640 )

2024-04-02 11:33:29 -07:00

__init__.py

Fix import warning (#479 )

2024-02-27 08:47:56 -08:00

convert.py

add dequantize option to mlx_lm/convert.py (#547 )

2024-03-19 19:50:08 -07:00

fuse.py

feat(mlx-lm): export the GGUF (fp16) format model weights from fuse.py (#555 )

2024-03-21 10:34:11 -07:00

generate.py

chore(mlx-lm): enable to apply default chat template (#577 )

2024-03-20 21:39:39 -07:00

gguf.py

fix(mlx-lm): type hints in gguf.py (#621 )

2024-03-26 07:56:01 -07:00

LORA.md

feat(mlx-lm): export the GGUF (fp16) format model weights from fuse.py (#555 )

2024-03-21 10:34:11 -07:00

lora.py

Configurable LR schedulers (#604 )

2024-03-29 13:41:10 -07:00

MERGE.md

Support for slerp merging models (#455 )

2024-02-19 20:37:15 -08:00

merge.py

feat: add update_config functionality (#531 )

2024-03-14 06:36:05 -07:00

py.typed

Add py.typed to support PEP-561 (type-hinting) (#389 )

2024-01-30 21:17:38 -08:00

README.md

feat: move lora into mlx-lm (#337 )

2024-01-23 08:44:37 -08:00

requirements.txt

Switch to fast RMS/LN Norm (#603 )

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

sample_utils.py

fix(mlx-lm): sorted probs in top_p implementation. (#610 )

2024-03-25 15:07:55 -07:00

SERVER.md

Prevent llms/mlx_lm from serving the local directory as a webserver (#498 )

2024-02-27 19:40:42 -08:00

server.py

Set finish_reason in response (#592 )

2024-03-19 20:21:26 -07:00

UPLOAD.md

Mlx llm package (#301 )

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

utils.py

cleanup whisper a little (#639 )

2024-03-30 13:13:58 -07:00

version.py

feat(mlx-lm): export the GGUF (fp16) format model weights from fuse.py (#555 )

2024-03-21 10:34:11 -07:00

README.md

Generate Text with MLX and 🤗 Hugging Face

This an example of large language model text generation that can pull models from the Hugging Face Hub.

For more information on this example, see the README in the parent directory.

This package also supports fine tuning with LoRA or QLoRA. For more information see the LoRA documentation.