File size: 4,290 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
# coding=utf-8
# 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.

import json
import os
from collections import OrderedDict
from typing import Any, Dict, Optional

import fire
import torch
from safetensors.torch import save_file
from tqdm import tqdm
from transformers.modeling_utils import (
    SAFE_WEIGHTS_INDEX_NAME,
    SAFE_WEIGHTS_NAME,
    WEIGHTS_INDEX_NAME,
    WEIGHTS_NAME,
    shard_checkpoint,
)


CONFIG_NAME = "config.json"


def save_weight(input_dir: str, output_dir: str, shard_size: str, save_safetensors: bool):
    baichuan2_state_dict: Dict[str, torch.Tensor] = OrderedDict()
    for filepath in tqdm(os.listdir(input_dir), desc="Load weights"):
        if os.path.isfile(os.path.join(input_dir, filepath)) and filepath.endswith(".bin"):
            shard_weight = torch.load(os.path.join(input_dir, filepath), map_location="cpu")
            baichuan2_state_dict.update(shard_weight)

    llama2_state_dict: Dict[str, torch.Tensor] = OrderedDict()
    for key, value in tqdm(baichuan2_state_dict.items(), desc="Convert format"):
        if "W_pack" in key:
            proj_size = value.size(0) // 3
            llama2_state_dict[key.replace("W_pack", "q_proj")] = value[:proj_size, :]
            llama2_state_dict[key.replace("W_pack", "k_proj")] = value[proj_size : 2 * proj_size, :]
            llama2_state_dict[key.replace("W_pack", "v_proj")] = value[2 * proj_size :, :]
        elif "lm_head" in key:
            llama2_state_dict[key] = torch.nn.functional.normalize(value)
        else:
            llama2_state_dict[key] = value

    weights_name = SAFE_WEIGHTS_NAME if save_safetensors else WEIGHTS_NAME
    shards, index = shard_checkpoint(llama2_state_dict, max_shard_size=shard_size, weights_name=weights_name)

    for shard_file, shard in tqdm(shards.items(), desc="Save weights"):
        if save_safetensors:
            save_file(shard, os.path.join(output_dir, shard_file), metadata={"format": "pt"})
        else:
            torch.save(shard, os.path.join(output_dir, shard_file))

    if index is None:
        print("Model weights saved in {}".format(os.path.join(output_dir, WEIGHTS_NAME)))
    else:
        index_name = SAFE_WEIGHTS_INDEX_NAME if save_safetensors else WEIGHTS_INDEX_NAME
        with open(os.path.join(output_dir, index_name), "w", encoding="utf-8") as f:
            json.dump(index, f, indent=2, sort_keys=True)
        print("Model weights saved in {}".format(output_dir))


def save_config(input_dir: str, output_dir: str):
    with open(os.path.join(input_dir, CONFIG_NAME), "r", encoding="utf-8") as f:
        llama2_config_dict: Dict[str, Any] = json.load(f)

    llama2_config_dict["architectures"] = ["LlamaForCausalLM"]
    llama2_config_dict.pop("auto_map", None)
    llama2_config_dict.pop("tokenizer_class", None)
    llama2_config_dict["model_type"] = "llama"

    with open(os.path.join(output_dir, CONFIG_NAME), "w", encoding="utf-8") as f:
        json.dump(llama2_config_dict, f, indent=2)
    print("Model config saved in {}".format(os.path.join(output_dir, CONFIG_NAME)))


def llamafy_baichuan2(
    input_dir: str, output_dir: str, shard_size: Optional[str] = "2GB", save_safetensors: Optional[bool] = False
):
    r"""
    Converts the Baichuan2-7B model in the same format as LLaMA2-7B.
    Usage: python llamafy_baichuan2.py --input_dir input --output_dir output
    Converted model: https://huggingface.co/hiyouga/Baichuan2-7B-Base-LLaMAfied
    """
    try:
        os.makedirs(output_dir, exist_ok=False)
    except Exception as e:
        raise print("Output dir already exists", e)

    save_weight(input_dir, output_dir, shard_size, save_safetensors)
    save_config(input_dir, output_dir)


if __name__ == "__main__":
    fire.Fire(llamafy_baichuan2)