Instructions to use mozilla-ai/llava-v1.5-7b-llamafile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mozilla-ai/llava-v1.5-7b-llamafile 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 mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
# Run inference directly in the terminal:
llama cli -hf mozilla-ai/llava-v1.5-7b-llamafile:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
# Run inference directly in the terminal:
llama cli -hf mozilla-ai/llava-v1.5-7b-llamafile: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 mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf mozilla-ai/llava-v1.5-7b-llamafile: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 mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mozilla-ai/llava-v1.5-7b-llamafile:Q8_0

Use Docker

docker model run hf.co/mozilla-ai/llava-v1.5-7b-llamafile:Q8_0

LM Studio
Jan
Ollama
How to use mozilla-ai/llava-v1.5-7b-llamafile with Ollama:
```
ollama run hf.co/mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
```

Unsloth Studio

How to use mozilla-ai/llava-v1.5-7b-llamafile 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 mozilla-ai/llava-v1.5-7b-llamafile 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 mozilla-ai/llava-v1.5-7b-llamafile to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mozilla-ai/llava-v1.5-7b-llamafile to start chatting

Atomic Chat new
Docker Model Runner
How to use mozilla-ai/llava-v1.5-7b-llamafile with Docker Model Runner:
```
docker model run hf.co/mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
```

Lemonade

How to use mozilla-ai/llava-v1.5-7b-llamafile with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mozilla-ai/llava-v1.5-7b-llamafile:Q8_0

Run and chat with the model

lemonade run user.llava-v1.5-7b-llamafile-Q8_0

List all available models

lemonade list

any special config files?

by ysdj - opened Feb 5, 2024

Discussion

ysdj

Feb 5, 2024

Hey Justine,
Thanks for the upload!
I'm trying to run it on my local machine but (perhaps due to my limited knowledge in GGUF models), I can't get it to work. I'm trying to load it locally via transformers (I can't run Ctransformers), and using the original config files but getting an error:
Unrecognized configuration class <class 'transformers.models.llava.configuration_llava.LlavaConfig'> for this kind of AutoModel: AutoModelForCausalLM.
any advice?

gatepoet

Mar 1, 2024

Update your Transformers package. The one referenced does not support AutoModel

pip install -U transformers

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment