File size: 8,063 Bytes
7762e8f |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 |
"""
Comprehensive script to publish model and codebase to Hugging Face Hub
"""
import argparse
import os
import sys
from pathlib import Path
from huggingface_hub import HfApi, create_repo, upload_folder, upload_file
from transformers import AutoTokenizer, AutoModelForSequenceClassification
# Add parent directory to path
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
def publish_to_hub(
model_path: str,
repo_id: str,
private: bool = False,
upload_code: bool = True,
upload_model: bool = True
):
"""
Publish model and codebase to Hugging Face Hub.
Args:
model_path: Path to the trained model
repo_id: Full repository ID (e.g., "username/repo-name")
private: Whether to make the repository private
upload_code: Whether to upload code files
upload_model: Whether to upload the model
"""
print("=" * 70)
print("Publishing to Hugging Face Hub")
print("=" * 70)
print(f"\nRepository: {repo_id}")
print(f"Private: {private}")
print(f"Upload Model: {upload_model}")
print(f"Upload Code: {upload_code}")
api = HfApi()
# Create repository
print("\n[1/4] Creating/verifying repository...")
try:
create_repo(
repo_id=repo_id,
repo_type="model",
exist_ok=True,
private=private
)
print(f"✓ Repository ready: {repo_id}")
except Exception as e:
print(f"✗ Error creating repository: {e}")
print("\nMake sure you're logged in:")
print(" huggingface-cli login")
return False
# Upload model and tokenizer
if upload_model:
print("\n[2/4] Uploading model and tokenizer...")
try:
if not os.path.exists(model_path):
print(f"✗ Model path not found: {model_path}")
print(" Skipping model upload. You can upload it later.")
else:
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForSequenceClassification.from_pretrained(model_path)
model.push_to_hub(repo_id)
tokenizer.push_to_hub(repo_id)
print("✓ Model and tokenizer uploaded")
except Exception as e:
print(f"✗ Error uploading model: {e}")
print(" You can upload the model separately later.")
else:
print("\n[2/4] Skipping model upload (--no-model flag)")
# Upload code files
if upload_code:
print("\n[3/4] Uploading code files...")
try:
repo_root = Path(__file__).parent.parent
# Files to upload
code_files = [
"train.py",
"inference.py",
"config.yaml",
"requirements.txt",
"setup.py",
"README.md",
"MODEL_CARD.md",
"LICENSE",
".gitignore"
]
# Directories to upload
code_dirs = [
"src",
"scripts"
]
uploaded_count = 0
# Upload individual files
for file_name in code_files:
file_path = repo_root / file_name
if file_path.exists():
try:
upload_file(
path_or_fileobj=str(file_path),
path_in_repo=file_name,
repo_id=repo_id,
repo_type="model"
)
print(f" ✓ Uploaded {file_name}")
uploaded_count += 1
except Exception as e:
print(f" ⚠ Could not upload {file_name}: {e}")
# Upload directories
for dir_name in code_dirs:
dir_path = repo_root / dir_name
if dir_path.exists() and dir_path.is_dir():
try:
upload_folder(
folder_path=str(dir_path),
path_in_repo=dir_name,
repo_id=repo_id,
repo_type="model",
ignore_patterns=["__pycache__", "*.pyc", ".DS_Store"]
)
print(f" ✓ Uploaded {dir_name}/")
uploaded_count += 1
except Exception as e:
print(f" ⚠ Could not upload {dir_name}/: {e}")
print(f"\n✓ Uploaded {uploaded_count} code files/directories")
except Exception as e:
print(f"✗ Error uploading code: {e}")
else:
print("\n[3/4] Skipping code upload (--no-code flag)")
# Final summary
print("\n[4/4] Publishing complete!")
print("\n" + "=" * 70)
print("Success! 🎉")
print("=" * 70)
print(f"\nYour model is now available at:")
print(f"https://huggingface.co/{repo_id}")
if upload_model:
print("\nTo use your model:")
print(f"""
from transformers import pipeline
classifier = pipeline("text-classification", model="{repo_id}")
# Classify a comment
result = classifier("This function uses dynamic programming for O(n) time complexity")
print(result)
""")
return True
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Publish model and codebase to Hugging Face Hub",
formatter_class=argparse.RawDescriptionHelpFormatter,
epilog="""
Examples:
# Publish everything (model + code)
python scripts/publish_to_hub.py --repo-id Snaseem2026/code-comment-classifier
# Publish only code (no model)
python scripts/publish_to_hub.py --repo-id Snaseem2026/code-comment-classifier --no-model
# Publish only model (no code)
python scripts/publish_to_hub.py --repo-id Snaseem2026/code-comment-classifier --no-code
# Private repository
python scripts/publish_to_hub.py --repo-id Snaseem2026/code-comment-classifier --private
"""
)
parser.add_argument(
"--model-path",
type=str,
default="./results/final_model",
help="Path to the trained model"
)
parser.add_argument(
"--repo-id",
type=str,
default="Snaseem2026/code-comment-classifier",
help="Full repository ID (e.g., 'username/repo-name')"
)
parser.add_argument(
"--private",
action="store_true",
help="Make the repository private"
)
parser.add_argument(
"--no-code",
action="store_true",
help="Skip uploading code files"
)
parser.add_argument(
"--no-model",
action="store_true",
help="Skip uploading model files"
)
parser.add_argument(
"--yes",
action="store_true",
help="Skip confirmation prompt"
)
args = parser.parse_args()
print("\n" + "=" * 70)
print("Hugging Face Hub Publishing")
print("=" * 70)
print("\nBefore publishing, make sure you:")
print("1. Have a Hugging Face account")
print("2. Are logged in: huggingface-cli login")
print("3. Have reviewed MODEL_CARD.md and README.md")
print(f"4. Model path exists: {args.model_path} ({'✓' if os.path.exists(args.model_path) else '✗'})")
if not args.yes:
print("\n" + "=" * 70)
response = input(f"\nProceed with publishing to {args.repo_id}? (yes/no): ")
if response.lower() not in ['yes', 'y']:
print("Publishing cancelled.")
sys.exit(0)
success = publish_to_hub(
model_path=args.model_path,
repo_id=args.repo_id,
private=args.private,
upload_code=not args.no_code,
upload_model=not args.no_model
)
if not success:
sys.exit(1)
|