Instructions to use IgorGent/Vid with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use IgorGent/Vid with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="IgorGent/Vid", filename="thesby_Qwen2.5-VL-7B-NSFW-Caption-V3-bf16.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use IgorGent/Vid 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 IgorGent/Vid:BF16 # Run inference directly in the terminal: llama cli -hf IgorGent/Vid:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf IgorGent/Vid:BF16 # Run inference directly in the terminal: llama cli -hf IgorGent/Vid:BF16
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 IgorGent/Vid:BF16 # Run inference directly in the terminal: ./llama-cli -hf IgorGent/Vid:BF16
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 IgorGent/Vid:BF16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf IgorGent/Vid:BF16
Use Docker
docker model run hf.co/IgorGent/Vid:BF16
- LM Studio
- Jan
- Ollama
How to use IgorGent/Vid with Ollama:
ollama run hf.co/IgorGent/Vid:BF16
- Unsloth Studio
How to use IgorGent/Vid 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 IgorGent/Vid 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 IgorGent/Vid to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for IgorGent/Vid to start chatting
- Atomic Chat new
- Docker Model Runner
How to use IgorGent/Vid with Docker Model Runner:
docker model run hf.co/IgorGent/Vid:BF16
- Lemonade
How to use IgorGent/Vid with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull IgorGent/Vid:BF16
Run and chat with the model
lemonade run user.Vid-BF16
List all available models
lemonade list
| import requests | |
| import os | |
| class SendVideoToBackend: | |
| def INPUT_TYPES(s): | |
| return { | |
| "required": { | |
| "filenames": ("VHS_FILENAMES",), | |
| "url": ("STRING", {"default": "http://your-backend.com/api/upload"}), | |
| "field_name": ("STRING", {"default": "video"}), | |
| }, | |
| "optional": { | |
| "auth_token": ("STRING", {"default": ""}), | |
| } | |
| } | |
| RETURN_TYPES = ("STRING",) | |
| FUNCTION = "send_video" | |
| OUTPUT_NODE = True | |
| CATEGORY = "Backend" | |
| def send_video(self, filenames, url, field_name, auth_token=""): | |
| # Ищем именно mp4 файл в списке путей | |
| file_path = None | |
| for path in filenames[1]: | |
| if path.lower().endswith(".mp4"): | |
| file_path = path | |
| break | |
| # Если mp4 не нашли, берем первый доступный файл | |
| if file_path is None: | |
| file_path = filenames[1][0] | |
| if not os.path.exists(file_path): | |
| return (f"Error: File {file_path} not found",) | |
| headers = {} | |
| if auth_token: | |
| headers["Authorization"] = f"Bearer {auth_token}" | |
| # Определяем правильный MIME-тип в зависимости от расширения | |
| mime_type = 'video/mp4' if file_path.lower().endswith(".mp4") else 'image/png' | |
| with open(file_path, 'rb') as f: | |
| files = {field_name: (os.path.basename(file_path), f, mime_type)} | |
| response = requests.post(url, files=files, headers=headers) | |
| if response.status_code == 200: | |
| return (f"Success: {response.text}",) | |
| else: | |
| return (f"Error {response.status_code}: {response.text}",) | |
| NODE_CLASS_MAPPINGS = {"SendVideoToBackend": SendVideoToBackend} | |
| NODE_DISPLAY_NAME_MAPPINGS = {"SendVideoToBackend": "🚀 Send Video to Backend"} |