Instructions to use mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF with Transformers:

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF 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 mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-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 mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-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 mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Great work, can't wait to test!

by boneylizardwizard - opened May 15, 2024

Discussion

boneylizardwizard

May 15, 2024

•

edited May 15, 2024

You literally uploaded the first ever useable looking llama3 70b gguf uncensored model in real time as I was searching for this exact thing. Thanks for your amazing timing and many efforts!

(Not your doing but the other llama3 70b gguf uncensored you uploaded wasn't decensored very effectively in the first instance)

mradermacher

Owner May 15, 2024

•

edited May 15, 2024

Good to know - and, yeah, I noticed the others were not very good, too. Somehow I overlooked this one when it came out.

OpenSourceAnarchist

May 15, 2024

Yes thanks again for quantizing this one, I've had my eye on it but didn't feel like learning the quant process for it. I always rely on your uploads, thank you so much :)

mradermacher

Owner May 15, 2024

Quanting was so easy what I started doing it. At the moment, it's a total mess.

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