Instructions to use mys/ggml_llava-v1.5-7b 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 mys/ggml_llava-v1.5-7b 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 mys/ggml_llava-v1.5-7b:F16 # Run inference directly in the terminal: llama cli -hf mys/ggml_llava-v1.5-7b:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf mys/ggml_llava-v1.5-7b:F16 # Run inference directly in the terminal: llama cli -hf mys/ggml_llava-v1.5-7b:F16
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 mys/ggml_llava-v1.5-7b:F16 # Run inference directly in the terminal: ./llama-cli -hf mys/ggml_llava-v1.5-7b:F16
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 mys/ggml_llava-v1.5-7b:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf mys/ggml_llava-v1.5-7b:F16
Use Docker
docker model run hf.co/mys/ggml_llava-v1.5-7b:F16
- LM Studio
- Jan
- Ollama
How to use mys/ggml_llava-v1.5-7b with Ollama:
ollama run hf.co/mys/ggml_llava-v1.5-7b:F16
- Unsloth Desktop
- Docker Model Runner
How to use mys/ggml_llava-v1.5-7b with Docker Model Runner:
docker model run hf.co/mys/ggml_llava-v1.5-7b:F16
- Lemonade
How to use mys/ggml_llava-v1.5-7b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull mys/ggml_llava-v1.5-7b:F16
Run and chat with the model
lemonade run user.ggml_llava-v1.5-7b-F16
List all available models
lemonade list
- Atomic Chat
Help getting Llavar working
Hello,
First of all, ty for your contributions to this community. I've been very excited to be able to use the Llava model because of the files you uploaded. I wanted to make a request - would it be possible for you to help with the Llavar conversion? Llavar is a very promising Llava variant that appears to do text recognition quite well: https://llavar.github.io/
I've started a discussion thread on Llama.cpp, with details of my approach.
I'm not sure if a conversion is not possible yet or it's user error on my part:
https://github.com/ggerganov/llama.cpp/discussions/3875
Any assistance you could provide would greatly aid me and I'm sure others who are struggling with this.
Thanks!