Instructions to use microsoft/bitnet-b1.58-2B-4T-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/bitnet-b1.58-2B-4T-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/bitnet-b1.58-2B-4T-bf16", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/bitnet-b1.58-2B-4T-bf16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("microsoft/bitnet-b1.58-2B-4T-bf16", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/bitnet-b1.58-2B-4T-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/bitnet-b1.58-2B-4T-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/bitnet-b1.58-2B-4T-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/bitnet-b1.58-2B-4T-bf16

SGLang

How to use microsoft/bitnet-b1.58-2B-4T-bf16 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 "microsoft/bitnet-b1.58-2B-4T-bf16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/bitnet-b1.58-2B-4T-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "microsoft/bitnet-b1.58-2B-4T-bf16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/bitnet-b1.58-2B-4T-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/bitnet-b1.58-2B-4T-bf16 with Docker Model Runner:
```
docker model run hf.co/microsoft/bitnet-b1.58-2B-4T-bf16
```

Model is functionally retarded

by MilitantHitchhiker - opened May 8, 2025

Discussion

MilitantHitchhiker

May 8, 2025

This model is functionally retarded and cannot complete objective tasks related to speech and language.

MarxismLeninism

May 9, 2025

Kinda of expected for a model of this size if you want average (and not above average sota performance) model have to be at least 7B

MarxismLeninism

May 9, 2025

It well known for neural network that the lower the base number you use fastest it is ie base 1, base 2 and base 3. Done alot work on this for simple nn they also only class of instant trained instant inference nn. However replicating that as base 1 transformers (nobody done this well I have, unary is fastest, not sure why it but just is) followed by binary, tenary etc.

MarxismLeninism

May 9, 2025

They also difficult to get right as well

MilitantHitchhiker

May 10, 2025

The problem is the training data and objectively invalid "safety" enforcement.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment