Instructions to use BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf")
model = AutoModelForCausalLM.from_pretrained("BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf 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 BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf:F32
# Run inference directly in the terminal:
llama cli -hf BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf:F32

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf:F32
# Run inference directly in the terminal:
llama cli -hf BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf:F32

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf:F32
# Run inference directly in the terminal:
./build/bin/llama cli -hf BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf:F32

Use Docker

docker model run hf.co/BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf:F32

Llama new
LM Studio
Jan

vLLM

How to use BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf:F32

SGLang

How to use BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf with Ollama:
```
ollama run hf.co/BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf:F32
```
Unsloth Desktop
Docker Model Runner
How to use BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf with Docker Model Runner:
```
docker model run hf.co/BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf:F32
```

Lemonade

How to use BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf:F32

Run and chat with the model

lemonade run user.bitnet_b1_58-xl_q8_0_gguf-F32

List all available models

lemonade list

Atomic Chat

This is a reproduction of the BitNet b1.58 paper. The models are trained with RedPajama dataset for 100B tokens. The hypers, as well as two-stage LR and weight decay, are implemented as suggested in their following paper. All models are open-source in the repo. We will train larger models and/or more tokens when resource is available.

Results

PPL and zero-shot accuracy:

Models	PPL	ARCe	ARCc	HS	BQ	OQ	PQ	WGe	Avg
FP16 700M (reported)	12.33	54.7	23.0	37.0	60.0	20.2	68.9	54.8	45.5
BitNet b1.58 700M (reported)	12.87	51.8	21.4	35.1	58.2	20.0	68.1	55.2	44.3
BitNet b1.58 700M (reproduced)	12.78	51.4	21.8	35.0	59.6	20.6	67.5	55.4	44.5
FP16 1.3B (reported)	11.25	56.9	23.5	38.5	59.1	21.6	70.0	53.9	46.2
BitNet b1.58 1.3B (reported)	11.29	54.9	24.2	37.7	56.7	19.6	68.8	55.8	45.4
BitNet b1.58 1.3B (reproduced)	11.19	55.8	23.7	37.6	59.0	20.2	69.2	56.0	45.9
FP16 3B (reported)	10.04	62.1	25.6	43.3	61.8	24.6	72.1	58.2	49.7
BitNet b1.58 3B (reported)	9.91	61.4	28.3	42.9	61.5	26.6	71.5	59.3	50.2
BitNet b1.58 3B (reproduced)	9.88	60.9	28.0	42.3	58.3	26.0	71.4	60.3	49.6

The differences between the reported numbers and the reproduced results are possibly variances from the training data processing, seeds, or other random factors.

Evaluation

You can now run with model with llama.cpp

Downloads last month: 467

GGUF

Model size

1B params

Architecture

bitnet

Hardware compatibility

8-bit

32-bit

Paper for BoscoTheDog/bitnet_b1_58-xl_q8_0_gguf

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 632