CLI cleanup and documentation (#2244)

* CLI init refactor

* fix

* cleanup and (partial) docs

* Adding documentation and continuing cleanup (in progress)

* remove finetune.py script

* continued cleanup and documentation

* pytest fixes

* review comments

* fix

* Fix

* typing fixes

* make sure the batch dataset patcher for multipack is always loaded when handling datasets

* review comments

* fix

---------

Co-authored-by: Dan Saunders <dan@axolotl.ai>
Co-authored-by: Wing Lian <wing@axolotl.ai>
This commit is contained in:
Dan Saunders
2025-01-13 12:55:29 -05:00
committed by GitHub
parent f89e962119
commit 1ed4de73b6
60 changed files with 1269 additions and 1259 deletions

View File

@@ -6,8 +6,8 @@ import logging
import os
import unittest
from axolotl.cli import load_datasets
from axolotl.common.cli import TrainerCliArgs
from axolotl.cli.args import TrainerCliArgs
from axolotl.common.datasets import load_datasets
from axolotl.train import train
from axolotl.utils.config import normalize_config
from axolotl.utils.dict import DictDefault
@@ -65,7 +65,7 @@ class TestPhi(unittest.TestCase):
cli_args = TrainerCliArgs()
dataset_meta = load_datasets(cfg=cfg, cli_args=cli_args)
train(cfg=cfg, cli_args=cli_args, dataset_meta=dataset_meta)
train(cfg=cfg, dataset_meta=dataset_meta)
check_model_output_exists(temp_dir, cfg)
@with_temp_dir
@@ -114,5 +114,5 @@ class TestPhi(unittest.TestCase):
cli_args = TrainerCliArgs()
dataset_meta = load_datasets(cfg=cfg, cli_args=cli_args)
train(cfg=cfg, cli_args=cli_args, dataset_meta=dataset_meta)
train(cfg=cfg, dataset_meta=dataset_meta)
check_model_output_exists(temp_dir, cfg)