Instructions to use calcuis/llava-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use calcuis/llava-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="calcuis/llava-gguf",
	filename="llava-f16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use calcuis/llava-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf calcuis/llava-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf calcuis/llava-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf calcuis/llava-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf calcuis/llava-gguf:Q4_K_M

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 calcuis/llava-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf calcuis/llava-gguf:Q4_K_M

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 calcuis/llava-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf calcuis/llava-gguf:Q4_K_M

Use Docker

docker model run hf.co/calcuis/llava-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use calcuis/llava-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "calcuis/llava-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "calcuis/llava-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/calcuis/llava-gguf:Q4_K_M

Ollama
How to use calcuis/llava-gguf with Ollama:
```
ollama run hf.co/calcuis/llava-gguf:Q4_K_M
```

Unsloth Studio new

How to use calcuis/llava-gguf 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 calcuis/llava-gguf 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 calcuis/llava-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for calcuis/llava-gguf to start chatting

Docker Model Runner
How to use calcuis/llava-gguf with Docker Model Runner:
```
docker model run hf.co/calcuis/llava-gguf:Q4_K_M
```

Lemonade

How to use calcuis/llava-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull calcuis/llava-gguf:Q4_K_M

Run and chat with the model

lemonade run user.llava-gguf-Q4_K_M

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

llava: computer vision GGUF

Clip Handler > mmproj-f16.gguf (624MB)
Vision Model > llava-***.gguf (opt anyone you like)
provide a link of picture as prompt
it will probably give hints to you for complying your text-to-image prompt (reverse engineering) 🎃

how to use

compatible with gguf-connector (ggc v) 👻
see initial test examples (with just Q2_K - 2.53GB) below

prompt test#1

prompt picture URL: https://raw.githubusercontent.com/calcuis/comfy/master/sd3.5g.png

response: "The image features a computer screen displaying a cartoon of a woman with a fox head, sitting at a dining table. The table is set with a cake, a knife, and a cup, giving the impression that the woman is about to enjoy a meal. The cartoon is displayed in a graphic style, making it visually appealing and engaging."

prompt test#2

prompt picture URL: https://raw.githubusercontent.com/calcuis/suko-puzzle/master/demo.png

response: "The image shows a close-up of a cell phone screen, displaying a game board with a puzzle. The game board is filled with numbers, and there are four
different colored circles surrounding the puzzle. The game appears to be a popular one, as the image is taken from the perspective of someone looking at the screen."

prompt test#3

prompt picture URL: https://raw.githubusercontent.com/calcuis/gguf-connector/master/gguf.gif

response: "The image features a green cartoon character with a mouth wide open, appearing to be yawning. The character has a toothy smile and is wearing a pair of
yellow gloves. The overall scene is a colorful and fun representation of the green character."

feedback from connector: "Awesome!"

Downloads last month: 424

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for calcuis/llava-gguf

Quantizations

1 model