Instructions to use cortexso/llava-v1.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cortexso/llava-v1.6 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cortexso/llava-v1.6",
	filename="llava-v1.6-vicuna-7b-f16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use cortexso/llava-v1.6 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 cortexso/llava-v1.6:F16
# Run inference directly in the terminal:
llama cli -hf cortexso/llava-v1.6:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cortexso/llava-v1.6:F16
# Run inference directly in the terminal:
llama cli -hf cortexso/llava-v1.6: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 cortexso/llava-v1.6:F16
# Run inference directly in the terminal:
./llama-cli -hf cortexso/llava-v1.6: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 cortexso/llava-v1.6:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/llava-v1.6:F16

Use Docker

docker model run hf.co/cortexso/llava-v1.6:F16

LM Studio
Jan

vLLM

How to use cortexso/llava-v1.6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortexso/llava-v1.6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cortexso/llava-v1.6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cortexso/llava-v1.6:F16

Ollama
How to use cortexso/llava-v1.6 with Ollama:
```
ollama run hf.co/cortexso/llava-v1.6:F16
```

Unsloth Studio

How to use cortexso/llava-v1.6 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 cortexso/llava-v1.6 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 cortexso/llava-v1.6 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cortexso/llava-v1.6 to start chatting

Atomic Chat new
Docker Model Runner
How to use cortexso/llava-v1.6 with Docker Model Runner:
```
docker model run hf.co/cortexso/llava-v1.6:F16
```

Lemonade

How to use cortexso/llava-v1.6 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cortexso/llava-v1.6:F16

Run and chat with the model

lemonade run user.llava-v1.6-F16

List all available models

lemonade list

Overview

LLaVA (Large Language and Vision Assistant) is an open-source chatbot trained to handle multimodal instruction-following tasks. It is a fine-tuned Vicuna-7B model, designed to process both text and image inputs. This auto-regressive language model leverages the transformer architecture to improve interactions in vision-language tasks, making it useful for research in computer vision, natural language processing, machine learning, and artificial intelligence.

LLaVA-v1.6-Vicuna-7B is the latest iteration, trained in December 2023, and optimized for improved instruction-following performance in multimodal settings.

Variants

No	Variant	Cortex CLI command
1	llava-v1.6-vicuna-7b-f16	`cortex run llava-v1.6:gguf-f16`
2	llava-v1.6-vicuna-7b-q4_km	`cortex run llava-v1.6:gguf-q4-km`

Use it with Jan (UI)

Install Jan using Quickstart
Use in Jan model Hub:
```
cortexso/llava-v1.6
```

Use it with Cortex (CLI)

Install Cortex using Quickstart
Run the model with command:
```
cortex run llava-v1.6
```

Credits

Author: LLaVA Research Team
Converter: Homebrew
Original License: LLAMA 2 Community License
Papers: LLaVA-v1.6: Enhancing Large Multimodal Models

Downloads last month: 19

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

16-bit