Instructions to use FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF", dtype="auto")

llama-cpp-python

How to use FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF",
	filename="Llama-3.1-Unhinged-Vision-8B-f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF: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 FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF: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 FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF:F16

Use Docker

docker model run hf.co/FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF:F16

LM Studio
Jan
Ollama
How to use FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF with Ollama:
```
ollama run hf.co/FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF:F16
```

Unsloth Studio

How to use FiditeNemini/Llama-3.1-Unhinged-Vision-8B-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 FiditeNemini/Llama-3.1-Unhinged-Vision-8B-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 FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF to start chatting

Docker Model Runner
How to use FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF:F16
```

Lemonade

How to use FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF:F16

Run and chat with the model

lemonade run user.Llama-3.1-Unhinged-Vision-8B-GGUF-F16

List all available models

lemonade list

Meta Llama 3.1 8B Model Combination

This is an ablated Meta Llama 3.1 8B model, combined with a mmprojector model designed for Llama 3.0, converted to GGUF.

The base Llama 3.1 appears to have been trained on multimodal content, and with the new 128K context, seems to have the necessary context to be able to talk about at least two separate images in a chat without confusing the two.

Downloads last month: 615

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

8-bit

16-bit

32-bit

Inference Providers NEW

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