File size: 4,999 Bytes
2852136
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
# Copyright 2024 the LlamaFactory team.
#
# 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 typing import TYPE_CHECKING, Any, Dict, List, Optional

import torch
from transformers import PreTrainedModel

from ..data import get_template_and_fix_tokenizer
from ..extras.callbacks import LogCallback
from ..extras.logging import get_logger
from ..hparams import get_infer_args, get_train_args
from ..model import load_model, load_tokenizer
from .dpo import run_dpo
from .kto import run_kto
from .ppo import run_ppo
from .pt import run_pt
from .rm import run_rm
from .sft import run_sft


if TYPE_CHECKING:
    from transformers import TrainerCallback


logger = get_logger(__name__)


def run_exp(args: Optional[Dict[str, Any]] = None, callbacks: List["TrainerCallback"] = []) -> None:
    model_args, data_args, training_args, finetuning_args, generating_args = get_train_args(args)
    callbacks.append(LogCallback(training_args.output_dir))

    if finetuning_args.stage == "pt":
        run_pt(model_args, data_args, training_args, finetuning_args, callbacks)
    elif finetuning_args.stage == "sft":
        run_sft(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
    elif finetuning_args.stage == "rm":
        run_rm(model_args, data_args, training_args, finetuning_args, callbacks)
    elif finetuning_args.stage == "ppo":
        run_ppo(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
    elif finetuning_args.stage == "dpo":
        run_dpo(model_args, data_args, training_args, finetuning_args, callbacks)
    elif finetuning_args.stage == "kto":
        run_kto(model_args, data_args, training_args, finetuning_args, callbacks)
    else:
        raise ValueError("Unknown task.")


def export_model(args: Optional[Dict[str, Any]] = None) -> None:
    model_args, data_args, finetuning_args, _ = get_infer_args(args)

    if model_args.export_dir is None:
        raise ValueError("Please specify `export_dir` to save model.")

    if model_args.adapter_name_or_path is not None and model_args.export_quantization_bit is not None:
        raise ValueError("Please merge adapters before quantizing the model.")

    tokenizer_module = load_tokenizer(model_args)
    tokenizer = tokenizer_module["tokenizer"]
    processor = tokenizer_module["processor"]
    get_template_and_fix_tokenizer(tokenizer, data_args.template)
    model = load_model(tokenizer, model_args, finetuning_args)  # must after fixing tokenizer to resize vocab

    if getattr(model, "quantization_method", None) and model_args.adapter_name_or_path is not None:
        raise ValueError("Cannot merge adapters to a quantized model.")

    if not isinstance(model, PreTrainedModel):
        raise ValueError("The model is not a `PreTrainedModel`, export aborted.")

    if getattr(model, "quantization_method", None) is None:  # cannot convert dtype of a quantized model
        output_dtype = getattr(model.config, "torch_dtype", torch.float16)
        setattr(model.config, "torch_dtype", output_dtype)
        model = model.to(output_dtype)
    else:
        setattr(model.config, "torch_dtype", torch.float16)

    model.save_pretrained(
        save_directory=model_args.export_dir,
        max_shard_size="{}GB".format(model_args.export_size),
        safe_serialization=(not model_args.export_legacy_format),
    )
    if model_args.export_hub_model_id is not None:
        model.push_to_hub(
            model_args.export_hub_model_id,
            token=model_args.hf_hub_token,
            max_shard_size="{}GB".format(model_args.export_size),
            safe_serialization=(not model_args.export_legacy_format),
        )

    try:
        tokenizer.padding_side = "left"  # restore padding side
        tokenizer.init_kwargs["padding_side"] = "left"
        tokenizer.save_pretrained(model_args.export_dir)
        if model_args.export_hub_model_id is not None:
            tokenizer.push_to_hub(model_args.export_hub_model_id, token=model_args.hf_hub_token)

        if model_args.visual_inputs and processor is not None:
            getattr(processor, "image_processor").save_pretrained(model_args.export_dir)
            if model_args.export_hub_model_id is not None:
                getattr(processor, "image_processor").push_to_hub(
                    model_args.export_hub_model_id, token=model_args.hf_hub_token
                )

    except Exception:
        logger.warning("Cannot save tokenizer, please copy the files manually.")