Instructions to use VladHong/llama-cpp-K2-FAST2 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 VladHong/llama-cpp-K2-FAST2 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 VladHong/llama-cpp-K2-FAST2 # Run inference directly in the terminal: llama cli -hf VladHong/llama-cpp-K2-FAST2
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf VladHong/llama-cpp-K2-FAST2 # Run inference directly in the terminal: llama cli -hf VladHong/llama-cpp-K2-FAST2
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf VladHong/llama-cpp-K2-FAST2 # Run inference directly in the terminal: ./build/bin/llama cli -hf VladHong/llama-cpp-K2-FAST2
Use Docker
docker model run hf.co/VladHong/llama-cpp-K2-FAST2
- Llama new
- LM Studio
- Jan
- Ollama
How to use VladHong/llama-cpp-K2-FAST2 with Ollama:
ollama run hf.co/VladHong/llama-cpp-K2-FAST2
- Unsloth Desktop
- Docker Model Runner
How to use VladHong/llama-cpp-K2-FAST2 with Docker Model Runner:
docker model run hf.co/VladHong/llama-cpp-K2-FAST2
- Lemonade
How to use VladHong/llama-cpp-K2-FAST2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull VladHong/llama-cpp-K2-FAST2
Run and chat with the model
lemonade run user.llama-cpp-K2-FAST2-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Download examples/model-conversion/scripts/utils/hf-create-collection.py from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 3.45 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/examples/model-conversion/scripts/utils/hf-create-collection.py
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/examples/model-conversion/scripts/utils/hf-create-collection.py
-
curl -L -o hf-create-collection.py https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/examples/model-conversion/scripts/utils/hf-create-collection.py
3.45 kB
| #!/usr/bin/env python3 | |
| from huggingface_hub import HfApi | |
| import argparse | |
| import os | |
| import sys | |
| def create_collection(title, description, private=False, namespace=None, return_slug=False): | |
| """ | |
| Create a new collection on Hugging Face | |
| Args: | |
| title: Collection title | |
| description: Collection description | |
| private: Whether the collection should be private (default: False) | |
| namespace: Optional namespace (defaults to your username) | |
| Returns: | |
| Collection object if successful, None if failed | |
| """ | |
| # Check if HF_TOKEN is available | |
| token = os.getenv("HF_TOKEN") or os.getenv("HUGGINGFACE_HUB_TOKEN") | |
| if not token: | |
| print("β No HF_TOKEN or HUGGINGFACE_HUB_TOKEN found in environment variables") | |
| print("Please set your Hugging Face token as an environment variable") | |
| return None | |
| # Initialize API | |
| api = HfApi() | |
| try: | |
| # Test authentication first | |
| user_info = api.whoami() | |
| if not return_slug: | |
| print(f"β Authenticated as: {user_info['name']}") | |
| # Create the collection | |
| if not return_slug: | |
| print(f"π Creating collection: '{title}'...") | |
| collection = api.create_collection( | |
| title=title, | |
| description=description, | |
| private=private, | |
| namespace=namespace | |
| ) | |
| if not return_slug: | |
| print(f"β Collection created successfully!") | |
| print(f"π Collection slug: {collection.slug}") | |
| print(f"π Collection URL: https://huggingface.co/collections/{collection.slug}") | |
| return collection | |
| except Exception as e: | |
| print(f"β Error creating collection: {e}") | |
| return None | |
| def main(): | |
| # This script requires that the environment variable HF_TOKEN is set with your | |
| # Hugging Face API token. | |
| api = HfApi() | |
| parser = argparse.ArgumentParser(description='Create a Huggingface Collection') | |
| parser.add_argument('--name', '-n', help='The name/title of the Collection', required=True) | |
| parser.add_argument('--description', '-d', help='The description for the Collection', required=True) | |
| parser.add_argument('--namespace', '-ns', help='The namespace to add the Collection to', required=True) | |
| parser.add_argument('--private', '-p', help='Create a private Collection', action='store_true') # Fixed | |
| parser.add_argument('--return-slug', '-s', help='Only output the collection slug', action='store_true') # Fixed | |
| args = parser.parse_args() | |
| name = args.name | |
| description = args.description | |
| private = args.private | |
| namespace = args.namespace | |
| return_slug = args.return_slug | |
| if not return_slug: | |
| print("π Creating Hugging Face Collection") | |
| print(f"Title: {name}") | |
| print(f"Description: {description}") | |
| print(f"Namespace: {namespace}") | |
| print(f"Private: {private}") | |
| collection = create_collection( | |
| title=name, | |
| description=description, | |
| private=private, | |
| namespace=namespace, | |
| return_slug=return_slug | |
| ) | |
| if collection: | |
| if return_slug: | |
| print(collection.slug) | |
| else: | |
| print("\nπ Collection created successfully!") | |
| print(f"Use this slug to add models: {collection.slug}") | |
| else: | |
| print("\nβ Failed to create collection") | |
| sys.exit(1) | |
| if __name__ == "__main__": | |
| main() | |