Instructions to use parrishcorcoran/MedusaBitNet-2B-4T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use parrishcorcoran/MedusaBitNet-2B-4T with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="parrishcorcoran/MedusaBitNet-2B-4T",
	filename="ggml-model-i2_s-medusa.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use parrishcorcoran/MedusaBitNet-2B-4T 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 parrishcorcoran/MedusaBitNet-2B-4T
# Run inference directly in the terminal:
llama cli -hf parrishcorcoran/MedusaBitNet-2B-4T

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf parrishcorcoran/MedusaBitNet-2B-4T
# Run inference directly in the terminal:
llama cli -hf parrishcorcoran/MedusaBitNet-2B-4T

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 parrishcorcoran/MedusaBitNet-2B-4T
# Run inference directly in the terminal:
./llama-cli -hf parrishcorcoran/MedusaBitNet-2B-4T

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 parrishcorcoran/MedusaBitNet-2B-4T
# Run inference directly in the terminal:
./build/bin/llama-cli -hf parrishcorcoran/MedusaBitNet-2B-4T

Use Docker

docker model run hf.co/parrishcorcoran/MedusaBitNet-2B-4T

LM Studio
Jan

vLLM

How to use parrishcorcoran/MedusaBitNet-2B-4T with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "parrishcorcoran/MedusaBitNet-2B-4T"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "parrishcorcoran/MedusaBitNet-2B-4T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/parrishcorcoran/MedusaBitNet-2B-4T

Ollama
How to use parrishcorcoran/MedusaBitNet-2B-4T with Ollama:
```
ollama run hf.co/parrishcorcoran/MedusaBitNet-2B-4T
```

Unsloth Studio

How to use parrishcorcoran/MedusaBitNet-2B-4T 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 parrishcorcoran/MedusaBitNet-2B-4T 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 parrishcorcoran/MedusaBitNet-2B-4T to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for parrishcorcoran/MedusaBitNet-2B-4T to start chatting

Atomic Chat new
Docker Model Runner
How to use parrishcorcoran/MedusaBitNet-2B-4T with Docker Model Runner:
```
docker model run hf.co/parrishcorcoran/MedusaBitNet-2B-4T
```

Lemonade

How to use parrishcorcoran/MedusaBitNet-2B-4T with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull parrishcorcoran/MedusaBitNet-2B-4T

Run and chat with the model

lemonade run user.MedusaBitNet-2B-4T-{{QUANT_TAG}}

List all available models

lemonade list

MedusaBitNet-2B-4T / .gitattributes

Parrish Corcoran

Add trained Medusa heads and merged GGUF model

734ed40 4 months ago

Raw

History Blame Contribute Delete

2.29 kB

	*.7z filter=lfs diff=lfs merge=lfs -text
	*.arrow filter=lfs diff=lfs merge=lfs -text
	*.bin filter=lfs diff=lfs merge=lfs -text
	*.bz2 filter=lfs diff=lfs merge=lfs -text
	*.ckpt filter=lfs diff=lfs merge=lfs -text
	*.ftz filter=lfs diff=lfs merge=lfs -text
	*.gz filter=lfs diff=lfs merge=lfs -text
	*.h5 filter=lfs diff=lfs merge=lfs -text
	*.joblib filter=lfs diff=lfs merge=lfs -text
	.lfs. filter=lfs diff=lfs merge=lfs -text
	*.mlmodel filter=lfs diff=lfs merge=lfs -text
	*.model filter=lfs diff=lfs merge=lfs -text
	*.msgpack filter=lfs diff=lfs merge=lfs -text
	*.npy filter=lfs diff=lfs merge=lfs -text
	*.npz filter=lfs diff=lfs merge=lfs -text
	*.onnx filter=lfs diff=lfs merge=lfs -text
	*.ot filter=lfs diff=lfs merge=lfs -text
	*.parquet filter=lfs diff=lfs merge=lfs -text
	*.pb filter=lfs diff=lfs merge=lfs -text
	*.pickle filter=lfs diff=lfs merge=lfs -text
	*.pkl filter=lfs diff=lfs merge=lfs -text
	*.pt filter=lfs diff=lfs merge=lfs -text
	*.pth filter=lfs diff=lfs merge=lfs -text
	*.rar filter=lfs diff=lfs merge=lfs -text
	*.safetensors filter=lfs diff=lfs merge=lfs -text
	saved_model/*/ filter=lfs diff=lfs merge=lfs -text
	.tar. filter=lfs diff=lfs merge=lfs -text
	*.tar filter=lfs diff=lfs merge=lfs -text
	*.tflite filter=lfs diff=lfs merge=lfs -text
	*.tgz filter=lfs diff=lfs merge=lfs -text
	*.wasm filter=lfs diff=lfs merge=lfs -text
	*.xz filter=lfs diff=lfs merge=lfs -text
	*.zip filter=lfs diff=lfs merge=lfs -text
	*.zst filter=lfs diff=lfs merge=lfs -text
	tfevents filter=lfs diff=lfs merge=lfs -text
	figures/architecture.png filter=lfs diff=lfs merge=lfs -text
	figures/energy_efficiency.png filter=lfs diff=lfs merge=lfs -text
	figures/head_accuracy.png filter=lfs diff=lfs merge=lfs -text
	figures/headtohead_throughput.png filter=lfs diff=lfs merge=lfs -text
	figures/hero_summary.png filter=lfs diff=lfs merge=lfs -text
	figures/medusa_speedup.png filter=lfs diff=lfs merge=lfs -text
	figures/memory_vs_energy.png filter=lfs diff=lfs merge=lfs -text
	figures/performance_summary.png filter=lfs diff=lfs merge=lfs -text
	figures/quality_vs_efficiency.png filter=lfs diff=lfs merge=lfs -text
	figures/status_transparency.png filter=lfs diff=lfs merge=lfs -text
	figures/throughput_vs_quality.png filter=lfs diff=lfs merge=lfs -text
	*.gguf filter=lfs diff=lfs merge=lfs -text