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")
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 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

nielsr

Aug 1, 2025

This PR enhances the model card by:

Adding the pipeline_tag: text-generation to the metadata, which ensures the model appears under the relevant filter on the Hugging Face Hub (huggingface.co/models?pipeline_tag=text-generation).
Updating the license to apache-2.0 (standard SPDX identifier) for clarity and consistency, as indicated by the project's GitHub repository, and removing the specific license_name and license_link fields which become redundant.
Removing the base_model metadata, as this model is a foundational 'base' model within the Falcon-H1 family, not a fine-tuned version of another model on the Hub.
Adding direct links to the Hugging Face paper page, the official GitHub repository, and the project homepage for easier navigation and improved discoverability of related resources.
Updating the license information within the model description for consistency with the metadata.

Improve model card: Add pipeline tag, update license, and add project links77474992

ybelkada

Technology Innovation Institute org Aug 4, 2025

Thanks @nielsr , for the license, can you revert it back to falcon-llm-license ?

Update README.md16ab3db3

Update README.mdf70aa3df

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment