Instructions to use Sicarius-Prototyping/Turbo_Grammar_51B_Alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sicarius-Prototyping/Turbo_Grammar_51B_Alpha with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Sicarius-Prototyping/Turbo_Grammar_51B_Alpha",
	filename="Turbo_Grammar_51B_Q6.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Sicarius-Prototyping/Turbo_Grammar_51B_Alpha with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Sicarius-Prototyping/Turbo_Grammar_51B_Alpha
# Run inference directly in the terminal:
llama-cli -hf Sicarius-Prototyping/Turbo_Grammar_51B_Alpha

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Sicarius-Prototyping/Turbo_Grammar_51B_Alpha
# Run inference directly in the terminal:
llama-cli -hf Sicarius-Prototyping/Turbo_Grammar_51B_Alpha

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 Sicarius-Prototyping/Turbo_Grammar_51B_Alpha
# Run inference directly in the terminal:
./llama-cli -hf Sicarius-Prototyping/Turbo_Grammar_51B_Alpha

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 Sicarius-Prototyping/Turbo_Grammar_51B_Alpha
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Sicarius-Prototyping/Turbo_Grammar_51B_Alpha

Use Docker

docker model run hf.co/Sicarius-Prototyping/Turbo_Grammar_51B_Alpha

LM Studio
Jan
Ollama
How to use Sicarius-Prototyping/Turbo_Grammar_51B_Alpha with Ollama:
```
ollama run hf.co/Sicarius-Prototyping/Turbo_Grammar_51B_Alpha
```

Unsloth Studio new

How to use Sicarius-Prototyping/Turbo_Grammar_51B_Alpha 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 Sicarius-Prototyping/Turbo_Grammar_51B_Alpha 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 Sicarius-Prototyping/Turbo_Grammar_51B_Alpha to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Sicarius-Prototyping/Turbo_Grammar_51B_Alpha to start chatting

Docker Model Runner
How to use Sicarius-Prototyping/Turbo_Grammar_51B_Alpha with Docker Model Runner:
```
docker model run hf.co/Sicarius-Prototyping/Turbo_Grammar_51B_Alpha
```

Lemonade

How to use Sicarius-Prototyping/Turbo_Grammar_51B_Alpha with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Sicarius-Prototyping/Turbo_Grammar_51B_Alpha

Run and chat with the model

lemonade run user.Turbo_Grammar_51B_Alpha-{{QUANT_TAG}}

List all available models

lemonade list

POC of an advanced tool to fix grammar, perform advanced GEC (grammar error correction), write poems and analyze them, emulate any author writing style. This is in prototyping because I did not have enough time to make it bullet proof and stable enough to warrant under my flagship models. Very usable, but not stable, feel free to play with it or improve it.

Downloads last month: 1

GGUF

Model size

52B params

Architecture

deci

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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