Instructions to use mradermacher/Llama3.1-70b-Uncensored-i1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Llama3.1-70b-Uncensored-i1-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Llama3.1-70b-Uncensored-i1-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Llama3.1-70b-Uncensored-i1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Llama3.1-70b-Uncensored-i1-GGUF",
	filename="Llama3.1-70b-Uncensored.i1-IQ1_M.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 mradermacher/Llama3.1-70b-Uncensored-i1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/Llama3.1-70b-Uncensored-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Llama3.1-70b-Uncensored-i1-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 mradermacher/Llama3.1-70b-Uncensored-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Llama3.1-70b-Uncensored-i1-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/Llama3.1-70b-Uncensored-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Llama3.1-70b-Uncensored-i1-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/Llama3.1-70b-Uncensored-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Llama3.1-70b-Uncensored-i1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Llama3.1-70b-Uncensored-i1-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Llama3.1-70b-Uncensored-i1-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 mradermacher/Llama3.1-70b-Uncensored-i1-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 mradermacher/Llama3.1-70b-Uncensored-i1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/Llama3.1-70b-Uncensored-i1-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use mradermacher/Llama3.1-70b-Uncensored-i1-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Llama3.1-70b-Uncensored-i1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Llama3.1-70b-Uncensored-i1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama3.1-70b-Uncensored-i1-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on Feb 21

Commit

777ca92

verified ·

1 Parent(s): 812ab2b

auto-patch README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -46,6 +46,7 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-Q2_K_S.gguf) | i1-Q2_K_S | 24.6 | very low quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
@@ -57,6 +58,7 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-Q6_K.gguf) | i1-Q6_K | 58.0 | practically like static Q6_K |
 Here is a handy graph by ikawrakow comparing some lower-quality quant

 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-Q2_K_S.gguf) | i1-Q2_K_S | 24.6 | very low quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama3.1-70b-Uncensored-i1-GGUF/resolve/main/Llama3.1-70b-Uncensored.i1-Q6_K.gguf) | i1-Q6_K | 58.0 | practically like static Q6_K |
 Here is a handy graph by ikawrakow comparing some lower-quality quant