Anupam Mediratta 5c89d1f6a6 Add instruct tuning support to LoRA training ... Fixes #484 Add support for instruct tuning with input/output pairs and alternative loss functions. * **llms/mlx_lm/lora.py** - Add `CompletionsDataset` class to support input/output pairs. - Modify `Dataset` class to handle different dataset types. - Update `main` function to include new dataset type. * **llms/mlx_lm/tuner/trainer.py** - Modify `default_loss` function to support alternative loss functions. - Add new `instruct_loss` function for instruct tuning. * **llms/mlx_lm/LORA.md** - Add instructions for instruct tuning with input/output pairs. - Update documentation to include alternative loss functions. * **llms/tests/test_datasets.py** - Add tests for `CompletionsDataset` and `create_dataset` functions. * **llms/tests/test_trainer.py** - Add tests for `default_loss` and `instruct_loss` functions. --- For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/ml-explore/mlx-examples/issues/484?shareId=XXXX-XXXX-XXXX-XXXX).		2025-01-20 11:42:13 +05:30
..
__init__.py	LoRA: Extract small function (#614)	2024-06-02 06:38:42 -07:00
datasets.py	Custom local dataset features (#1085)	2025-01-13 10:01:18 -08:00
dora.py	Feature: QDoRA (#891)	2024-09-30 08:01:11 -07:00
lora.py	Allow the entire model to be targed for LoRA and DoRA fine tuning: LoRA and DoRA embeddings with small DoRALinear bug fix (#914)	2024-08-16 07:38:36 -07:00
trainer.py	Add instruct tuning support to LoRA training	2025-01-20 11:42:13 +05:30
utils.py	add internlm3 (#1206)	2025-01-15 14:55:41 -08:00