Instructions to use TheDrummer/Rocinante-12B-v1.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheDrummer/Rocinante-12B-v1.1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheDrummer/Rocinante-12B-v1.1-GGUF",
	filename="Rocinante-12B-v1.1-BF16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use TheDrummer/Rocinante-12B-v1.1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheDrummer/Rocinante-12B-v1.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheDrummer/Rocinante-12B-v1.1-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 TheDrummer/Rocinante-12B-v1.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheDrummer/Rocinante-12B-v1.1-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 TheDrummer/Rocinante-12B-v1.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheDrummer/Rocinante-12B-v1.1-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 TheDrummer/Rocinante-12B-v1.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheDrummer/Rocinante-12B-v1.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheDrummer/Rocinante-12B-v1.1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TheDrummer/Rocinante-12B-v1.1-GGUF with Ollama:
```
ollama run hf.co/TheDrummer/Rocinante-12B-v1.1-GGUF:Q4_K_M
```

Unsloth Studio new

How to use TheDrummer/Rocinante-12B-v1.1-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 TheDrummer/Rocinante-12B-v1.1-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 TheDrummer/Rocinante-12B-v1.1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheDrummer/Rocinante-12B-v1.1-GGUF to start chatting

Docker Model Runner
How to use TheDrummer/Rocinante-12B-v1.1-GGUF with Docker Model Runner:
```
docker model run hf.co/TheDrummer/Rocinante-12B-v1.1-GGUF:Q4_K_M
```

Lemonade

How to use TheDrummer/Rocinante-12B-v1.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheDrummer/Rocinante-12B-v1.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Rocinante-12B-v1.1-GGUF-Q4_K_M

List all available models

lemonade list

Nbv9pQ88Xb

BeaverAI proudly presents...

Rocinante 12B v1.1 🚀

A versatile workhorse for any adventure!

Finding him so mettlesome, conceived a good omen from his eagerness, believing it a certain presage of his success in the dreadful adventure he was about to achieve.

He steered his course homeward; and Rocinante, as if he had guessed the knight’s intention, began to move with such alacrity and nimbleness, that his hooves scarcely seemed to touch the ground.

Description

If you would like a pure off-the-rails experience, try Rocinante 12B v1

Testers have reported:

Plenty of new and moistier words!
Richer and distinct prose
Cranked up creativity
Engaging and adventure-filled storytelling

Arsenal (Supported Chat Templates)

ChatML for RP
Alpaca for Story / Instruct Adventure
Mistral for NeMo
You can mix it up and see which works best for you.

Sampler Suggestions

Use DRY
Suggestion: Temp 0.7 for a chill, familiar ride. Temp 1.2 for a nitro boost!

Credit

Thank you for the compute, Garg!

Thank you for the Della merge, MarinaraSpaghetti!

Thank you Statuo for the EXL2 quants!

Downloads last month: 4,029

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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

TheDrummer
/

Rocinante-12B-v1.1-GGUF