Instructions to use tiiuae/Falcon-H1-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/Falcon-H1-3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="tiiuae/Falcon-H1-3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/Falcon-H1-3B-Instruct")
model = AutoModelForCausalLM.from_pretrained("tiiuae/Falcon-H1-3B-Instruct", device_map="auto")
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 tiiuae/Falcon-H1-3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/Falcon-H1-3B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/Falcon-H1-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiiuae/Falcon-H1-3B-Instruct

SGLang

How to use tiiuae/Falcon-H1-3B-Instruct 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 "tiiuae/Falcon-H1-3B-Instruct" \
    --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": "tiiuae/Falcon-H1-3B-Instruct",
		"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 "tiiuae/Falcon-H1-3B-Instruct" \
        --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": "tiiuae/Falcon-H1-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiiuae/Falcon-H1-3B-Instruct with Docker Model Runner:
```
docker model run hf.co/tiiuae/Falcon-H1-3B-Instruct
```

Improve model card: Add pipeline tag, update license, and add project links

by nielsr HF Staff - opened Aug 1, 2025

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

+15

-6

Files changed (1) hide show

README.md +15 -6

README.md CHANGED Viewed

@@ -1,5 +1,4 @@
 ---
-library_name: transformers
 language:
 - ar
 - cs
@@ -19,18 +18,28 @@ language:
 - sv
 - ur
 - zh
-tags:
-- falcon-h1
 license: other
 license_name: falcon-llm-license
-license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
-base_model: tiiuae/Falcon-H1-3B-Base
 inference: true
 ---
 <img src="https://huggingface.co/datasets/tiiuae/documentation-images/resolve/main/falcon_mamba/falcon-h1-logo.png" alt="drawing" width="800"/>
-#  Table of Contents
 0. [TL;DR](#TL;DR)
 1. [Model Details](#model-details)

 ---
 language:
 - ar
 - cs
 - sv
 - ur
 - zh
+library_name: transformers
 license: other
 license_name: falcon-llm-license
+tags:
+- falcon-h1
 inference: true
+pipeline_tag: text-generation
 ---
 <img src="https://huggingface.co/datasets/tiiuae/documentation-images/resolve/main/falcon_mamba/falcon-h1-logo.png" alt="drawing" width="800"/>
+# Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance
+## Links
+- 📄 [Paper on Hugging Face](https://huggingface.co/papers/2507.22448)
+- 💻 [Code on GitHub](https://github.com/tiiuae/Falcon-H1)
+- 🌐 [Project Homepage](https://tiiuae.github.io/Falcon-H1/)
+- 📰 [Release Blogpost](https://falcon-lm.github.io/blog/falcon-h1/)
+- 🎮 [Hugging Face Demo](https://huggingface.co/spaces/tiiuae/Falcon-H1-playground)
+- 💬 [Discord Server](https://discord.gg/trwMYP9PYm)
+# Table of Contents
 0. [TL;DR](#TL;DR)
 1. [Model Details](#model-details)