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

parrishcorcoran commited on Apr 13

Commit

0f4a2f7

verified ·

1 Parent(s): 0d3c0a7

Upload folder using huggingface_hub

Browse files

Files changed (14) hide show

.gitattributes +11 -0
figures/architecture.png +3 -0
figures/energy_efficiency.png +3 -0
figures/head_accuracy.png +3 -0
figures/headtohead_throughput.png +3 -0
figures/hero_summary.png +3 -0
figures/medusa_speedup.png +3 -0
figures/memory_vs_energy.png +3 -0
figures/performance_summary.png +3 -0
figures/pipeline_timeline.png +0 -0
figures/quality_vs_efficiency.png +3 -0
figures/status_transparency.png +3 -0
figures/throughput_vs_quality.png +3 -0
figures/training_loss.png +0 -0

@@ -33,3 +33,14 @@ saved_model/**/* 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

 *.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

parrishcorcoran
/

MedusaBitNet-2B-4T

Upload folder using huggingface_hub

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details