Falcon H1 34B Instruct GPTQ Int4

🚀 Falcon-H1 Transformer Model

The Falcon-H1 series is a family of hybrid-head language models developed by TII, offering high performance across various NLP tasks.

🚀 Quick Start

To quickly start using the Falcon-H1 model, you can choose from different libraries such as Hugging Face transformers, vLLM, or our custom fork of llama.cpp. The following sections provide detailed usage instructions.

✨ Features

• Hybrid Architecture: Combines Transformers and Mamba architecture for enhanced performance.
• Multilingual Support: Supports English and multiple other languages.
• High Performance: Performs well on a wide range of tasks, including reasoning, math, science, code, and instruction following.

📦 Installation

transformers

Install the latest version of transformers from source:

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

vLLM

Refer to the official vLLM documentation for more details on building vLLM from source.

llama.cpp

Install our fork of the llama.cpp library: https://github.com/tiiuae/llama.cpp-Falcon-H1. Use the same installing guidelines as llama.cpp.

💻 Usage Examples

Basic Usage

transformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "tiiuae/Falcon-H1-1B-Base"

model = AutoModelForCausalLM.from_pretrained(
  model_id,
  torch_dtype=torch.bfloat16,
  device_map="auto"
)

# Perform text generation

vLLM

Start a server using vLLM:

# pip install vllm
vllm serve tiiuae/Falcon-H1-1B-Instruct --tensor-parallel-size 2 --data-parallel-size 1

llama.cpp

Use our fork of llama.cpp library: https://github.com/tiiuae/llama.cpp-Falcon-H1.

📚 Documentation

Model Details

Training Details

For more details about the training protocol of this model, please refer to the Falcon-H1 technical blogpost.

Evaluation

Falcon-H1 series perform very well on a variety of tasks, including reasoning tasks.

You can check more in detail on our our release blogpost, detailed benchmarks.

Useful Links

• View our release blogpost.
• Feel free to join our discord server if you have any questions or to interact with our researchers and developers.

📄 License

This model is released under the Falcon-LLM License.

📚 Citation

If the Falcon-H1 family of models were helpful to your work, feel free to give us a cite.

@misc{tiifalconh1,
    title = {Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance},
    url = {https://falcon-lm.github.io/blog/falcon-h1},
    author = {Falcon-LLM Team},
    month = {May},
    year = {2025}
}