Spaces:
Running
on
Zero
Running
on
Zero
File size: 3,759 Bytes
19b19f0 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
#!/usr/bin/env python3
"""
Helper script to download the int4 model files at build time for Hugging Face Spaces
"""
import os
import sys
import subprocess
import logging
from pathlib import Path
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Model configuration
MAIN_MODEL_ID = "Tonic/petite-elle-L-aime-3-sft"
INT4_MODEL_ID = "Tonic/petite-elle-L-aime-3-sft/int4"
LOCAL_MODEL_PATH = "./int4"
def download_model():
"""Download the int4 model files to local directory"""
try:
logger.info(f"Downloading int4 model from {INT4_MODEL_ID}")
# Create local directory if it doesn't exist
os.makedirs(LOCAL_MODEL_PATH, exist_ok=True)
# Use huggingface_hub to download the model
from huggingface_hub import snapshot_download
# Download the int4 model files
snapshot_download(
repo_id=INT4_MODEL_ID,
local_dir=LOCAL_MODEL_PATH,
local_dir_use_symlinks=False,
ignore_patterns=["*.md", "*.txt", "*.git*", "*.ipynb", "*.py"]
)
logger.info(f"Model downloaded successfully to {LOCAL_MODEL_PATH}")
return True
except Exception as e:
logger.error(f"Error downloading model: {e}")
return False
def check_model_files():
"""Check if required model files exist"""
required_files = [
"config.json",
"pytorch_model.bin",
"tokenizer.json",
"tokenizer_config.json"
]
missing_files = []
for file in required_files:
file_path = os.path.join(LOCAL_MODEL_PATH, file)
if not os.path.exists(file_path):
missing_files.append(file)
if missing_files:
logger.error(f"Missing model files: {missing_files}")
return False
logger.info("All required model files found")
return True
def verify_model_integrity():
"""Verify that the downloaded model files are valid"""
try:
# Try to load the tokenizer to verify it's working
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(LOCAL_MODEL_PATH)
logger.info("Tokenizer loaded successfully from local files")
# Try to load the model config
from transformers import AutoConfig
config = AutoConfig.from_pretrained(LOCAL_MODEL_PATH)
logger.info("Model config loaded successfully from local files")
return True
except Exception as e:
logger.error(f"Error verifying model integrity: {e}")
return False
def main():
"""Main function to download model at build time"""
logger.info("Starting model download for Hugging Face Space...")
# Check if model files already exist
if check_model_files():
logger.info("Model files already exist, verifying integrity...")
if verify_model_integrity():
logger.info("Model files verified successfully")
return True
else:
logger.warning("Model files exist but failed integrity check, re-downloading...")
# Download the model
if download_model():
logger.info("Model download completed successfully")
# Verify the downloaded files
if check_model_files() and verify_model_integrity():
logger.info("Model download and verification completed successfully")
return True
else:
logger.error("Model download completed but verification failed")
return False
else:
logger.error("Model download failed")
return False
if __name__ == "__main__":
success = main()
sys.exit(0 if success else 1) |