File size: 2,805 Bytes
53d6bfb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
# Copyright 2020-2025 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer, Mxfp4Config

from trl import (
    ModelConfig,
    ScriptArguments,
    SFTConfig,
    SFTTrainer,
    TrlParser,
    get_peft_config,
)


def main(script_args, training_args, model_args):
    # ------------------------
    # Load model & tokenizer
    # ------------------------
    quantization_config = Mxfp4Config(dequantize=True)
    model_kwargs = dict(
        revision=model_args.model_revision,
        trust_remote_code=model_args.trust_remote_code,
        attn_implementation=model_args.attn_implementation,
        torch_dtype=model_args.torch_dtype,
        use_cache=False if training_args.gradient_checkpointing else True,
        quantization_config=quantization_config,
    )

    model = AutoModelForCausalLM.from_pretrained(
        model_args.model_name_or_path, **model_kwargs
    )

    tokenizer = AutoTokenizer.from_pretrained(
        model_args.model_name_or_path,
    )

    # --------------
    # Load dataset
    # --------------
    dataset = load_dataset(script_args.dataset_name, name=script_args.dataset_config)

    # -------------
    # Train model
    # -------------
    trainer = SFTTrainer(
        model=model,
        args=training_args,
        train_dataset=dataset[script_args.dataset_train_split],
        eval_dataset=dataset[script_args.dataset_test_split]
        if training_args.eval_strategy != "no"
        else None,
        # You had `processing_class` here, but SFTTrainer expects `tokenizer`
        tokenizer=tokenizer,
        peft_config=get_peft_config(model_args),
    )

    trainer.train()
    trainer.save_model(training_args.output_dir)
    if training_args.push_to_hub:
        # You had dataset_name here, but it's not a valid argument for push_to_hub in this context.
        # It will use the hub_model_id from TrainingArguments.
        trainer.push_to_hub()


if __name__ == "__main__":
    parser = TrlParser((ScriptArguments, SFTConfig, ModelConfig))
    script_args, training_args, model_args, _ = parser.parse_args_and_config(
        return_remaining_strings=True
    )
    main(script_args, training_args, model_args)