Instructions to use NoQuest/LLmSave with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use NoQuest/LLmSave with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf NoQuest/LLmSave:Q8_0 # Run inference directly in the terminal: llama cli -hf NoQuest/LLmSave:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf NoQuest/LLmSave:Q8_0 # Run inference directly in the terminal: llama cli -hf NoQuest/LLmSave:Q8_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf NoQuest/LLmSave:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf NoQuest/LLmSave:Q8_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf NoQuest/LLmSave:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf NoQuest/LLmSave:Q8_0
Use Docker
docker model run hf.co/NoQuest/LLmSave:Q8_0
- LM Studio
- Jan
- Ollama
How to use NoQuest/LLmSave with Ollama:
ollama run hf.co/NoQuest/LLmSave:Q8_0
- Unsloth Studio
How to use NoQuest/LLmSave with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for NoQuest/LLmSave to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for NoQuest/LLmSave to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for NoQuest/LLmSave to start chatting
- Atomic Chat new
- Docker Model Runner
How to use NoQuest/LLmSave with Docker Model Runner:
docker model run hf.co/NoQuest/LLmSave:Q8_0
- Lemonade
How to use NoQuest/LLmSave with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull NoQuest/LLmSave:Q8_0
Run and chat with the model
lemonade run user.LLmSave-Q8_0
List all available models
lemonade list
| 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!") | |