Instructions to use cjpais/llava-1.6-mistral-7b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cjpais/llava-1.6-mistral-7b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cjpais/llava-1.6-mistral-7b-gguf",
	filename="llava-1.6-mistral-7b.Q6_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cjpais/llava-1.6-mistral-7b-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cjpais/llava-1.6-mistral-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cjpais/llava-1.6-mistral-7b-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 cjpais/llava-1.6-mistral-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cjpais/llava-1.6-mistral-7b-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 cjpais/llava-1.6-mistral-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cjpais/llava-1.6-mistral-7b-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 cjpais/llava-1.6-mistral-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cjpais/llava-1.6-mistral-7b-gguf:Q4_K_M

Use Docker

docker model run hf.co/cjpais/llava-1.6-mistral-7b-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use cjpais/llava-1.6-mistral-7b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cjpais/llava-1.6-mistral-7b-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cjpais/llava-1.6-mistral-7b-gguf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/cjpais/llava-1.6-mistral-7b-gguf:Q4_K_M

Ollama
How to use cjpais/llava-1.6-mistral-7b-gguf with Ollama:
```
ollama run hf.co/cjpais/llava-1.6-mistral-7b-gguf:Q4_K_M
```

Unsloth Studio new

How to use cjpais/llava-1.6-mistral-7b-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 cjpais/llava-1.6-mistral-7b-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 cjpais/llava-1.6-mistral-7b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cjpais/llava-1.6-mistral-7b-gguf to start chatting

Docker Model Runner
How to use cjpais/llava-1.6-mistral-7b-gguf with Docker Model Runner:
```
docker model run hf.co/cjpais/llava-1.6-mistral-7b-gguf:Q4_K_M
```

Lemonade

How to use cjpais/llava-1.6-mistral-7b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cjpais/llava-1.6-mistral-7b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.llava-1.6-mistral-7b-gguf-Q4_K_M

List all available models

lemonade list

GGUF Quantized LLaVA 1.6 Mistral 7B

Updated quants and projector from PR #5267

Provided files

Name	Quant method	Bits	Size	Use case
llava-v1.6-mistral-7b.Q3_K_XS.gguf	Q3_K_XS	3	2.99 GB	very small, high quality loss
llava-v1.6-mistral-7b.Q3_K_M.gguf	Q3_K_M	3	3.52 GB	very small, high quality loss
llava-v1.6-mistral-7b.Q4_K_M.gguf	Q4_K_M	4	4.37 GB	medium, balanced quality - recommended
llava-v1.6-mistral-7b.Q5_K_S.gguf	Q5_K_S	5	5.00 GB	large, low quality loss - recommended
llava-v1.6-mistral-7b.Q5_K_M.gguf	Q5_K_M	5	5.13 GB	large, very low quality loss - recommended
llava-v1.6-mistral-7b.Q6_K.gguf	Q6_K	6	5.94 GB	very large, extremely low quality loss
llava-v1.6-mistral-7b.Q8_0.gguf	Q8_0	8	7.7 GB	very large, extremely low quality loss - not recommended

ORIGINAL LLaVA Model Card

Model details

Model type: LLaVA is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: mistralai/Mistral-7B-Instruct-v0.2

Model date: LLaVA-v1.6-Mistral-7B was trained in December 2023.

Paper or resources for more information: https://llava-vl.github.io/

License

mistralai/Mistral-7B-Instruct-v0.2 license.

Where to send questions or comments about the model: https://github.com/haotian-liu/LLaVA/issues

Intended use

Primary intended uses: The primary use of LLaVA is research on large multimodal models and chatbots.

Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

Training dataset

558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
158K GPT-generated multimodal instruction-following data.
500K academic-task-oriented VQA data mixture.
50K GPT-4V data mixture.
40K ShareGPT data.

Evaluation dataset

A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.

Downloads last month: 26,563

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

cjpais
/

llava-1.6-mistral-7b-gguf