Upload DownloadUploadble.py with huggingface_hub

DownloadUploadble.py

@@ -0,0 +1,102 @@
+
+from huggingface_hub import HfFolder, hf_hub_url
+import os
+import requests
+import tqdm
+from requests.adapters import HTTPAdapter
+from requests.exceptions import ConnectionError, RequestException, Timeout
+from tqdm.contrib.concurrent import thread_map
+from pathlib import Path
+import time
+
+
+# Save your token
+HfFolder.save_token('')  # Replace with your actual token
+
+# Define the repository to download from
+repo_id = "NoQuest/LLmSave"
+repo_type = "model"
+
+# Local path where you want to save the downloaded files
+local_folder_path = "./LLmSaveLocal"
+
+# Variable to specify the file or directory to download
+download_target = "fichiertemoin.txt"  # Change this to the desired file or directory name
+
+print(f"Downloading {download_target} from {repo_id} to {local_folder_path}...")
+
+# Create the local directory if it doesn't exist
+os.makedirs(local_folder_path, exist_ok=True)
+
+# Print the URL for debugging
+print(f"URL: {hf_hub_url(repo_id, download_target, repo_type=repo_type)}")
+
+def get_session(max_retries=5):
+    session = requests.Session()
+    if max_retries:
+        session.mount('https://cdn-lfs.huggingface.co', HTTPAdapter(max_retries=max_retries))
+        session.mount('https://huggingface.co', HTTPAdapter(max_retries=max_retries))
+    # ... (add authentication if needed)
+    return session
+
+def get_single_file(url, output_folder, start_from_scratch=False, max_retries=7):
+    filename = Path(url.rsplit('/', 1)[1])
+    output_path = output_folder / filename
+    attempt = 0
+    while attempt < max_retries:
+        attempt += 1
+        session = get_session()
+        headers = {}
+        mode = 'wb'
+        if output_path.exists() and not start_from_scratch:
+            # Resume download
+            r = session.get(url, stream=True, timeout=20)
+            total_size = int(r.headers.get('content-length', 0))
+            if output_path.stat().st_size >= total_size:
+                return
+            headers = {'Range': f'bytes={output_path.stat().st_size}-'}
+            mode = 'ab'
+        try:
+            with session.get(url, stream=True, headers=headers, timeout=30) as r:
+                r.raise_for_status()
+                total_size = int(r.headers.get('content-length', 0))
+                block_size = 1024 * 1024  # 1MB
+                tqdm_kwargs = {'total': total_size, 'unit': 'iB', 'unit_scale': True, 'bar_format': '{l_bar}{bar}|{n_fmt}/{total_fmt}{rate_fmt}'}
+                with open(output_path, mode) as f:
+                    with tqdm.tqdm(**tqdm_kwargs) as t:
+                        for data in r.iter_content(block_size):
+                            f.write(data)
+                            t.update(len(data))
+                break  # Exit loop if successful
+        except (RequestException, ConnectionError, Timeout) as e:
+            print(f"Error downloading {filename}: {e}.")
+            print(f"That was attempt {attempt}/{max_retries}.", end='')
+            if attempt < max_retries:
+                print(f"Retry begins in {2**attempt} seconds.")
+                time.sleep(2**attempt)
+            else:
+                print("Failed to download after the maximum number of attempts.")
+
+def start_download_threads(file_list, output_folder, start_from_scratch=False, threads=4):
+    thread_map(lambda url: get_single_file(url, output_folder, start_from_scratch=start_from_scratch), file_list, max_workers=threads, disable=True)
+
+def download_model_files(model, branch, links, output_folder, start_from_scratch=False, threads=4):
+    output_folder = Path(output_folder)
+    #output_folder.mkdir(parents=True, exist_ok=True)
+    output_folder.mkdir(parents=True, exist_ok=True)    
+
+    # ... (add metadata writing if needed)
+    print(f"Downloading the model to {output_folder}")
+    start_download_threads(links, output_folder, start_from_scratch=start_from_scratch, threads=threads)
+
+
+
+# Download the specified file or directory
+session = get_session()
+links = [hf_hub_url(repo_id, download_target, repo_type=repo_type)]
+
+branch = "main"
+
+download_model_files(repo_id, branch, links, local_folder_path)
+
+print("Download complete!")