Bitnet B1.58 2B 4T

🚀 BitNet b1.58 2B4T - Scaling Native 1-bit LLM

This repository hosts the weights for BitNet b1.58 2B4T, the world's first open-source, native 1-bit Large Language Model (LLM) with 2 billion parameters, developed by Microsoft Research. Trained on a 4-trillion-token corpus, it offers comparable performance to leading full - precision models while boasting significant computational efficiency.

🚀 Quick Start

This repository contains the weights for BitNet b1.58 2B4T, the first open - source, native 1 - bit Large Language Model (LLM) at the 2 - billion parameter scale, developed by Microsoft Research.

➡️ Technical Report: BitNet b1.58 2B4T Technical Report

➡️ Official Inference Code: microsoft/BitNet (bitnet.cpp)

✨ Features

• High Efficiency: Native 1 - bit quantization offers substantial advantages in computational efficiency (memory, energy, latency).
• Comparable Performance: Achieves performance comparable to leading open - weight, full - precision models of similar size.
• Multiple Training Stages: Undergoes pre - training, supervised fine - tuning, and direct preference optimization.

📦 Installation

Requirements

pip install git+https://github.com/huggingface/transformers.git@096f25ae1f501a084d8ff2dcaf25fbc2bd60eba4

💻 Usage Examples

Basic Usage

VERY IMPORTANT NOTE ON EFFICIENCY

⚠️ Important Note

Please do NOT expect performance efficiency gains (in terms of speed, latency, or energy consumption) when using this model with the standard transformers library, even with the required fork.

The current execution paths within transformers do not contain the specialized, highly optimized computational kernels required to leverage the advantages of the BitNet architecture. Running the model via transformers will likely result in inference speeds and energy usage comparable to, or potentially worse than, standard full - precision models within this framework on both CPU and GPU.

While you might observe reduced memory usage due to the quantized weights, the primary computational efficiency benefits are not accessible through this standard transformers usage path.

For achieving the efficiency benefits demonstrated in the technical paper, you MUST use the dedicated C++ implementation: bitnet.cpp.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "microsoft/bitnet-b1.58-2B-4T"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16
)

# Apply the chat template
messages = [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": "How are you?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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)

Advanced Usage

Please refer to the bitnet.cpp GitHub repository for detailed compilation steps, usage examples, and command - line options.

📚 Documentation

Model Variants

Several versions of the model weights are available on Hugging Face:

• microsoft/bitnet-b1.58-2B-4T (This repository): Contains the packed 1.58 - bit weights optimized for efficient inference. Use this for deployment.

• microsoft/bitnet-b1.58-2B-4T-bf16: Contains the master weights in BF16 format. Use this only for training or fine - tuning purposes.

• microsoft/bitnet-b1.58-2B-4T-gguf: Contains the model weights in GGUF format, compatible with the bitnet.cpp library for CPU inference.

Model Details

Evaluation

BitNet b1.58 2B4T was evaluated against leading open - weight full - precision LLMs of similar size. Below are the key results (all models are instruction - tuned versions):

*LLaMA 3.2 1B uses pruning & distillation.

**Gemma - 3 1B uses distillation.

📄 License

The model weights and code are released under the MIT License.

Bias, Risks, and Limitations

⚠️ Important Note

Predictions may perpetuate biases present in the training data. There is limited support for non - English languages and underrepresented domains. There is a risk of generating inaccurate or harmful content. The Bitnet model has an elevated defect rate when responding to election - critical queries, which may result in incorrect or unauthoritative election critical information being presented. We are working to improve the model's performance in this area. Users should verify information related to elections with the election authority in their region.

Disclaimer

💡 Usage Tip

We do not recommend using BitNet b1.58 in commercial or real - world applications without further testing and development. 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.