mlx-examples/llms/mlx_lm
alexC-nonsense4k 42458914c8
support dora finetune in mlx-examples/llms/mlx_lm (#779)
* support dora finetune

* solve problems in lora.py and tuner.utils.py

* add use_dora (bool) in functions of load adapters

* delete all unsupported quantization code and fix all the calculate problems in mlx_lm/tuner/dora.py

* Using stop_gradient to prevent gradients from flowing through ‘norm’ during backpropagation

* set DEFAULT_USE_DORA in mlx_lm/generate.py

* add annotation for all the use_dora

* mlx_lm/fuse.py support fuse dora layers and fix a bug of to_linear() in mlx_lm/tuner/dora.py

* simplify code of juding type of a fused layer in mlx_lm/fuse.py

* add use_dora in mlx_lm/fuse.py when apply_lora_layers()

* style + nits

* style + nits

* more updates

---------

Co-authored-by: chenyifei08 <chenyifei08@baidu.com>
Co-authored-by: Awni Hannun <awni@apple.com>
2024-05-16 08:21:26 -07:00
..
examples support dora finetune in mlx-examples/llms/mlx_lm (#779) 2024-05-16 08:21:26 -07:00
models Support non incremental kv cache growth (#766) 2024-05-15 12:56:24 -07:00
tuner support dora finetune in mlx-examples/llms/mlx_lm (#779) 2024-05-16 08:21:26 -07:00
__init__.py Fix import warning (#479) 2024-02-27 08:47:56 -08:00
convert.py Create executables for generate, lora, server, merge, convert (#682) 2024-04-16 16:08:49 -07:00
fuse.py support dora finetune in mlx-examples/llms/mlx_lm (#779) 2024-05-16 08:21:26 -07:00
generate.py support dora finetune in mlx-examples/llms/mlx_lm (#779) 2024-05-16 08:21:26 -07:00
gguf.py fix(mlx-lm): type hints in gguf.py (#621) 2024-03-26 07:56:01 -07:00
LORA.md MiniCPM implementation (#685) 2024-04-25 15:29:28 -07:00
lora.py support dora finetune in mlx-examples/llms/mlx_lm (#779) 2024-05-16 08:21:26 -07:00
MANAGE.md Add model management functionality for local caches (#736) 2024-05-03 12:20:13 -07:00
manage.py Add model management functionality for local caches (#736) 2024-05-03 12:20:13 -07:00
MERGE.md Create executables for generate, lora, server, merge, convert (#682) 2024-04-16 16:08:49 -07:00
merge.py Create executables for generate, lora, server, merge, convert (#682) 2024-04-16 16:08:49 -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 Quantize embedding / Update quantize API (#680) 2024-04-18 18:16:10 -07:00
sample_utils.py Use async eval (#670) 2024-04-11 13:18:23 -07:00
SERVER.md Validate server params & fix logit bias bug (#731) 2024-04-30 07:27:40 -07:00
server.py Add MLX Cache Limit setting for mlx_lm.generate and mlx_lm.server CLI (#744) 2024-05-03 12:42:48 -07:00
tokenizer_utils.py Kv cache (#643) 2024-05-08 08:18:13 -07:00
UPLOAD.md Mlx llm package (#301) 2024-01-12 10:25:56 -08:00
utils.py Add model_config parameter to load() and load_model() (#770) 2024-05-10 10:13:34 -07:00
version.py support dora finetune in mlx-examples/llms/mlx_lm (#779) 2024-05-16 08:21:26 -07:00

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.