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

Libraries

How to use microsoft/bitnet-b1.58-2B-4T 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", 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", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("microsoft/bitnet-b1.58-2B-4T", 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 Settings

vLLM

How to use microsoft/bitnet-b1.58-2B-4T 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"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use microsoft/bitnet-b1.58-2B-4T 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" \
    --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",
		"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" \
        --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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Add Hugging Face paper link and clarify repos

#13

by nielsr HF Staff - opened Apr 18, 2025

base: refs/heads/main

←

from: refs/pr/13

Discussion Files changed

-6

Files changed (1) hide show

README.md +7 -6

README.md CHANGED Viewed

@@ -1,15 +1,15 @@
 ---
-license: mit
-license_link: https://huggingface.co/microsoft/bitnet-b1.58-2B-4T/blob/main/LICENSE
 language:
 - en
 pipeline_tag: text-generation
 tags:
 - chat
 - bitnet
 - text-generation
 - large-language-model
-library_name: transformers
 ---
 # BitNet b1.58 2B4T - Scaling Native 1-bit LLM
@@ -18,7 +18,7 @@ This repository contains the weights for **BitNet b1.58 2B4T**, the first open-s
 Trained on a corpus of 4 trillion tokens, this model demonstrates that native 1-bit LLMs can achieve performance comparable to leading open-weight, full-precision models of similar size, while offering substantial advantages in computational efficiency (memory, energy, latency).
-➡️ **Technical Report:** [BitNet b1.58 2B4T Technical Report](https://arxiv.org/abs/2504.12285)
 ➡️ **Official Inference Code:** [microsoft/BitNet (bitnet.cpp)](https://github.com/microsoft/BitNet)
@@ -98,7 +98,8 @@ chat_input = tokenizer(prompt, return_tensors="pt").to(model.device)
 # Generate response
 chat_outputs = model.generate(**chat_input, max_new_tokens=50)
 response = tokenizer.decode(chat_outputs[0][chat_input['input_ids'].shape[-1]:], skip_special_tokens=True) # Decode only the response part
-print("\nAssistant Response:", response)
 ```
 ## How to Use (with `bitnet.cpp`)
@@ -141,4 +142,4 @@ BitNet b1.58 2B4T was evaluated against leading open-weight full-precision LLMs
 The model weights and code are released under the [MIT License](https://huggingface.co/microsoft/bitnet-b1.58-2B-4T/blob/main/LICENSE).
 ## Disclaimer
-This model is intended for research and development purposes. While efforts have been made to align it using SFT and DPO, it may still produce outputs that are unexpected, biased, or inaccurate. Please use responsibly.

 ---
 language:
 - en
+library_name: transformers
+license: mit
+license_link: https://huggingface.co/microsoft/bitnet-b1.58-2B-4T/blob/main/LICENSE
 pipeline_tag: text-generation
 tags:
 - chat
 - bitnet
 - text-generation
 - large-language-model
 ---
 # BitNet b1.58 2B4T - Scaling Native 1-bit LLM
 Trained on a corpus of 4 trillion tokens, this model demonstrates that native 1-bit LLMs can achieve performance comparable to leading open-weight, full-precision models of similar size, while offering substantial advantages in computational efficiency (memory, energy, latency).
+➡️ **Technical Report:** [BitNet b1.58 2B4T Technical Report](https://arxiv.org/abs/2504.12285) ➡️ **Hugging Face Paper:** [Hugging Face Paper](https://huggingface.co/papers/2504.12285)
 ➡️ **Official Inference Code:** [microsoft/BitNet (bitnet.cpp)](https://github.com/microsoft/BitNet)
 # Generate response
 chat_outputs = model.generate(**chat_input, max_new_tokens=50)
 response = tokenizer.decode(chat_outputs[0][chat_input['input_ids'].shape[-1]:], skip_special_tokens=True) # Decode only the response part
+print("
+Assistant Response:", response)
 ```
 ## How to Use (with `bitnet.cpp`)
 The model weights and code are released under the [MIT License](https://huggingface.co/microsoft/bitnet-b1.58-2B-4T/blob/main/LICENSE).
 ## Disclaimer
+This model is intended for research and development purposes. While efforts have been made to align it using SFT and DPO, it may still produce outputs that are unexpected, biased, or inaccurate. Please use responsibly.