How to use city96/umt5-xxl-encoder-gguf with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="city96/umt5-xxl-encoder-gguf", filename="umt5-xxl-encoder-F16.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
How to use city96/umt5-xxl-encoder-gguf with llama.cpp:
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf city96/umt5-xxl-encoder-gguf:Q4_K_M # Run inference directly in the terminal: llama-cli -hf city96/umt5-xxl-encoder-gguf:Q4_K_M
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf city96/umt5-xxl-encoder-gguf:Q4_K_M # Run inference directly in the terminal: llama-cli -hf city96/umt5-xxl-encoder-gguf:Q4_K_M
# 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 city96/umt5-xxl-encoder-gguf:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf city96/umt5-xxl-encoder-gguf:Q4_K_M
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 city96/umt5-xxl-encoder-gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf city96/umt5-xxl-encoder-gguf:Q4_K_M
docker model run hf.co/city96/umt5-xxl-encoder-gguf:Q4_K_M
How to use city96/umt5-xxl-encoder-gguf with Ollama:
ollama run hf.co/city96/umt5-xxl-encoder-gguf:Q4_K_M
How to use city96/umt5-xxl-encoder-gguf with Unsloth Studio:
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 city96/umt5-xxl-encoder-gguf to start chatting
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 city96/umt5-xxl-encoder-gguf to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for city96/umt5-xxl-encoder-gguf to start chatting
How to use city96/umt5-xxl-encoder-gguf with Docker Model Runner:
How to use city96/umt5-xxl-encoder-gguf with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull city96/umt5-xxl-encoder-gguf:Q4_K_M
lemonade run user.umt5-xxl-encoder-gguf-Q4_K_M
lemonade list
I had 4 total black videos today, it happened after I changed to the Q8 clip. Never happened before.
I'm running with the Wan 2.2 I2V Q6K, with Lightx2v
Same black screen video issue here with the Q8_0, Q6_K is fine
· Sign up or log in to comment
