apply_delta.py

"""
Usage:
python3 apply_delta.py --base /path/to/model_weights/llama-65b --target-model-path stabilityai/FreeWilly1-Delta-SafeTensor --delta models/FreeWilly1-Delta-SafeTensor
"""
import argparse

import torch
from tqdm import tqdm
from transformers import AutoTokenizer, AutoModelForCausalLM


def apply_delta(base_model_path, target_model_path, delta_path):
    print("Loading base model")
    base = AutoModelForCausalLM.from_pretrained(
        base_model_path, torch_dtype=torch.float16, low_cpu_mem_usage=True)

    print("Loading delta")
    delta = AutoModelForCausalLM.from_pretrained(delta_path, torch_dtype=torch.float16, low_cpu_mem_usage=True)
    delta_tokenizer = AutoTokenizer.from_pretrained(delta_path)

    base_tokenizer = AutoTokenizer.from_pretrained(base_model_path, use_fast=False)

    input_embeddings = base.get_input_embeddings().weight.data
    output_embeddings = base.get_output_embeddings().weight.data

    print("Applying delta")
    for name, param in tqdm(base.state_dict().items(), desc="Applying delta"):
        assert name in delta.state_dict()
        param.data += delta.state_dict()[name]

    print("Saving target model")
    base.save_pretrained(target_model_path)
    delta_tokenizer.save_pretrained(target_model_path)


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--base-model-path", type=str, required=True)
    parser.add_argument("--target-model-path", type=str, required=True)
    parser.add_argument("--delta-path", type=str, required=True)

    args = parser.parse_args()

    apply_delta(args.base_model_path, args.target_model_path, args.delta_path)