Instructions to use tiiuae/Falcon-H1-0.5B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/Falcon-H1-0.5B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="tiiuae/Falcon-H1-0.5B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/Falcon-H1-0.5B-Instruct")
model = AutoModelForCausalLM.from_pretrained("tiiuae/Falcon-H1-0.5B-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-H1-0.5B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/Falcon-H1-0.5B-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-H1-0.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiiuae/Falcon-H1-0.5B-Instruct

SGLang

How to use tiiuae/Falcon-H1-0.5B-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-H1-0.5B-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-H1-0.5B-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-H1-0.5B-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-H1-0.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiiuae/Falcon-H1-0.5B-Instruct with Docker Model Runner:
```
docker model run hf.co/tiiuae/Falcon-H1-0.5B-Instruct
```

Latest transformers version does not work

by supercharge19 - opened May 30, 2025

Discussion

supercharge19

May 30, 2025

ValueError: The checkpoint you are trying to load has model type `falcon_h1` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git`

>>> import transformers
>>> transformers.__version__
'4.52.4'

Please also note llama.cpp custom branch https://github.com/tiiuae/llama.cpp-Falcon-H1 does not work either (similar error, model architecture is not compatible for gguf version).

print_info: file format = GGUF V3 (latest)
print_info: file type   = Q5_0
print_info: file size   = 1.01 GiB (5.60 BPW)
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'falcon-h1'
llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model './models/Falcon-H1-1B-Instruct-Q5_0.gguf'
srv    load_model: failed to load model, './models/Falcon-H1-1B-Instruct-Q5_0.gguf'
srv    operator(): operator(): cleaning up before exit...
main: exiting due to model loading error

I hope this gets fixed soon not only for transformers but also for llamacpp, really excited to see model working.

ybelkada

Technology Innovation Institute org May 30, 2025

Hi @supercharge19
For now, please install transformers from source with the command in order to use the model:

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

At the next PyPi release of transformers, you'll be able to install it from PyPi directly pip install transformers

supercharge19

Jun 2, 2025

Thank you it worked. Ok, so it required 4.53.0.dev0 version.

supercharge19 changed discussion status to closed Jun 2, 2025

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

Tap or paste here to upload images

· Sign up or log in to comment