Instructions to use Green-Sky/bitnet_b1_58-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Green-Sky/bitnet_b1_58-3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Green-Sky/bitnet_b1_58-3B-GGUF",
	filename="bitnet_b1_58-3B.q1_3.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 Green-Sky/bitnet_b1_58-3B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Green-Sky/bitnet_b1_58-3B-GGUF
# Run inference directly in the terminal:
llama-cli -hf Green-Sky/bitnet_b1_58-3B-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Green-Sky/bitnet_b1_58-3B-GGUF
# Run inference directly in the terminal:
llama-cli -hf Green-Sky/bitnet_b1_58-3B-GGUF

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 Green-Sky/bitnet_b1_58-3B-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Green-Sky/bitnet_b1_58-3B-GGUF

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 Green-Sky/bitnet_b1_58-3B-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Green-Sky/bitnet_b1_58-3B-GGUF

Use Docker

docker model run hf.co/Green-Sky/bitnet_b1_58-3B-GGUF

LM Studio
Jan
Ollama
How to use Green-Sky/bitnet_b1_58-3B-GGUF with Ollama:
```
ollama run hf.co/Green-Sky/bitnet_b1_58-3B-GGUF
```

Unsloth Studio

How to use Green-Sky/bitnet_b1_58-3B-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 Green-Sky/bitnet_b1_58-3B-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 Green-Sky/bitnet_b1_58-3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Green-Sky/bitnet_b1_58-3B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Green-Sky/bitnet_b1_58-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/Green-Sky/bitnet_b1_58-3B-GGUF
```

Lemonade

How to use Green-Sky/bitnet_b1_58-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Green-Sky/bitnet_b1_58-3B-GGUF

Run and chat with the model

lemonade run user.bitnet_b1_58-3B-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Highly experimental, not for general consumption

The code needed to running this model, as well as the base model itself are not ready yet.

This is uploaded merely to help testing.

~~see https://github.com/ggerganov/llama.cpp/pull/7931~~

see https://github.com/ggerganov/llama.cpp/pull/8151 , the continued work by compilade, providing both 1.625bpw and 2bpw

This model is unsupported by the new TQ1_0 and TQ2_0 quants and the old formats havebeen/willbe removed. This model is unfortunaly sized inconvenient and is currently not supported by the new quants. see https://huggingface.co/Green-Sky/TriLM_3.9B-GGUF for a more up-to-date model and quant

Downloads last month: 47

GGUF

Model size

3B params

Architecture

bitnet

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

Model tree for Green-Sky/bitnet_b1_58-3B-GGUF

Base model

1bitLLM/bitnet_b1_58-3B

Quantized

(10)

this model