Delete main.py

main.py

@@ -1,247 +0,0 @@
-import argparse
-import os
-import shutil
-import subprocess
-import time
-from pathlib import Path
-
-from git import Repo
-
-
-def clone_hf_with_git(username: str, model_name: str, saved_dir: str):
-    full_model_name = f"{username}/{model_name}"
-    url = f"https://huggingface.co/{full_model_name}"
-    saved = f"{saved_dir}/{model_name}"
-
-    # perform `git lfs install`
-    subprocess.run(["git", "lfs", "install"])
-
-    print(f"[INFO] Cloning {model_name} from {url} ...")
-    Repo.clone_from(url, saved)
-
-
-def download_hf_with_git(full_name: str, saved_dir: str):
-    model_name = full_name.split("/")[1]
-    url = f"git@hf.co:{full_name}"
-    saved = f"{saved_dir}/{model_name}"
-
-    # perform `git lfs install`
-    subprocess.run(["git", "lfs", "install"])
-
-    print(f"Cloning {model_name} from {url} ...")
-    subprocess.run(["git", "clone", "--progress", url, saved])
-
-
-def convert_hf_to_gguf(
-    script_path: str,
-    dir_raw_model: str,
-    gguf_model_path: str,
-    pad_vocab: bool = False,
-):
-    if pad_vocab is True:
-        args = [
-            "--outfile",
-            gguf_model_path,
-            # "--vocab-type",
-            # "bpe",
-            "--pad-vocab",
-            dir_raw_model,
-        ]
-    else:
-        args = ["--outfile", gguf_model_path, dir_raw_model]
-        # convert.py for llama-3
-        # args = ["--outfile", gguf_model_path, "--vocab-type", "bpe", dir_raw_model]
-    res = subprocess.run(["python", script_path] + args)
-    print(res)
-
-
-def quantize_model(
-    quantizer: str,
-    f16_gguf_model_path: str,
-    quantized_gguf_model_path: str,
-    quant_type: str = "q4_0",
-):
-    print(f"[INFO] quantizer: {quantizer}")
-    print(f"[INFO] quant_type: {quant_type}")
-    print(f"[INFO] f16_gguf_model_path: {f16_gguf_model_path}")
-    print(f"[INFO] quantized_model_filename: {quantized_gguf_model_path}")
-    subprocess.run(
-        [
-            quantizer,
-            f16_gguf_model_path,
-            quantized_gguf_model_path,
-            quant_type,
-        ]
-    )
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Convert and quantize gguf models.")
-    parser.add_argument(
-        "--full-name",
-        type=str,
-        help="Huggingface model full name. e.g. `username/model_name`",
-    )
-    parser.add_argument(
-        "-s",
-        "--saved-dir",
-        type=str,
-        default="models",
-        help="The directory to save the model.",
-    )
-    parser.add_argument(
-        "--enable-converter",
-        action="store_true",
-        help="Enable the converter. Notice that `--converter` must be specified.",
-    )
-    parser.add_argument(
-        "-c",
-        "--converter",
-        type=str,
-        help="The path to the converter. Notice that `--enable-converter` must be specified if use this option.",
-    )
-    parser.add_argument(
-        "--pad-vocab",
-        action="store_true",
-        help="Enable adding pad tokens when model vocab expects more than tokenizer metadata provides. Notice that `--enable-converter` must be specified.",
-    )
-    parser.add_argument(
-        "--enable-quantizer",
-        action="store_true",
-        help="Enable the quantizer. Notice that `--quantizer` must be specified.",
-    )
-    parser.add_argument(
-        "-q",
-        "--quantizer",
-        type=str,
-        help="The path to the quantizer. Notice that `--enable-quantizer` must be specified if use this option.",
-    )
-    parser.add_argument(
-        "-t",
-        "--quant-type",
-        type=str,
-        default=None,
-        help="The quantization type. Notice that `--enable-quantizer` must be specified if use this option.",
-    )
-
-    args = parser.parse_args()
-
-    print(args)
-
-    print("Download model ...")
-    full_name = args.full_name
-    username, model_name = full_name.split("/")
-    saved_dir = args.saved_dir
-    # try:
-    #     download_hf_with_git(full_name, saved_dir)
-    #     print(f"The raw model is saved in {saved_dir}.")
-
-    # except Exception as e:
-    #     print(f"Failed to download model. {e}")
-    #     return
-
-    if args.enable_converter is True:
-        print("[CONVERTER] Convert model ...")
-        converter = args.converter
-
-        raw_model_dir = f"{saved_dir}/{model_name}"
-        print(f"[CONVERTER] raw_model_dir: {raw_model_dir}")
-
-        gguf_model_dir = Path(raw_model_dir).parent / f"{model_name}-gguf"
-        if not gguf_model_dir.exists():
-            gguf_model_dir.mkdir()
-        f16_gguf_model_path = gguf_model_dir / f"{model_name}-f16.gguf"
-
-        print(f"[CONVERTER] f16_gguf_model_path: {f16_gguf_model_path}")
-
-        # try:
-        #     convert_hf_to_gguf(
-        #         converter,
-        #         raw_model_dir,
-        #         str(f16_gguf_model_path),
-        #         args.pad_vocab,
-        #     )
-        #     print(f"The converted gguf model is saved in {f16_gguf_model_path}.")
-
-        # except Exception as e:
-        #     print(f"Failed to convert model. {e}")
-        #     return
-
-    if args.enable_quantizer is True:
-        print("[QUANTIZER] Quantize model ...")
-        quantizer = args.quantizer
-        print(f"[QUANTIZER] quantizer: {quantizer}")
-
-        if args.quant_type is not None:
-            quant_type = args.quant_type
-            quantized_gguf_model_path = (
-                gguf_model_dir / f"{model_name}-{quant_type}.gguf"
-            )
-
-            print(f"[QUANTIZER] quant_type: {quant_type}")
-            print(f"[QUANTIZER] quantized_model_filename: {quantized_gguf_model_path}")
-
-            try:
-                quantize_model(
-                    quantizer,
-                    str(f16_gguf_model_path),
-                    str(quantized_gguf_model_path),
-                    quant_type,
-                )
-                print(
-                    f"The quantized gguf model is saved in {quantized_gguf_model_path}."
-                )
-
-            except Exception as e:
-                print(e)
-                print("Failed to quantize model.")
-                return
-        else:
-            for quant_type in [
-                # "Q2_K",
-                # "Q3_K_L",
-                # "Q3_K_M",
-                # "Q3_K_S",
-                # "Q4_0",
-                # "Q4_K_M",
-                # "Q4_K_S",
-                # "Q5_0",
-                "Q5_K_M",
-                # "Q5_K_S",
-                "Q6_K",
-                "Q8_0",
-            ]:
-                quantized_gguf_model_path = (
-                    gguf_model_dir / f"{model_name}-{quant_type}.gguf"
-                )
-
-                print(f"[QUANTIZER] quant_type: {quant_type}")
-                print(
-                    f"[QUANTIZER] quantized_model_filename: {quantized_gguf_model_path}"
-                )
-
-                try:
-                    quantize_model(
-                        quantizer,
-                        str(f16_gguf_model_path),
-                        str(quantized_gguf_model_path),
-                        quant_type,
-                    )
-                    print(
-                        f"The quantized gguf model is saved in {quantized_gguf_model_path}."
-                    )
-
-                except Exception as e:
-                    print(e)
-                    print("Failed to quantize model.")
-                    return
-
-        # # remove the raw model dir for saving space
-        # print(f"The quantization is done. Remove {raw_model_dir}")
-        # shutil.rmtree(raw_model_dir)
-
-    print("Done.")
-
-
-if __name__ == "__main__":
-    main()