Instructions to use tiiuae/Falcon-H1-34B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/Falcon-H1-34B-Base with Transformers:

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

pipe = pipeline("text-generation", model="tiiuae/Falcon-H1-34B-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/Falcon-H1-34B-Base")
model = AutoModelForCausalLM.from_pretrained("tiiuae/Falcon-H1-34B-Base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiiuae/Falcon-H1-34B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/Falcon-H1-34B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/Falcon-H1-34B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tiiuae/Falcon-H1-34B-Base

SGLang

How to use tiiuae/Falcon-H1-34B-Base 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-H1-34B-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/Falcon-H1-34B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-H1-34B-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/Falcon-H1-34B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tiiuae/Falcon-H1-34B-Base with Docker Model Runner:
```
docker model run hf.co/tiiuae/Falcon-H1-34B-Base
```

Improve model card: Add pipeline tag, correct license, and enhance links

by nielsr HF Staff - opened Aug 1, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+15

-5

nielsr

Aug 1, 2025

This PR significantly improves the model card for the Falcon-H1 model by:

Adding the pipeline_tag: text-generation to the metadata, enabling better discoverability and filtering on the Hugging Face Hub.
Correcting the license metadata from other to apache-2.0, aligning with the explicit license stated in the official GitHub repository's README. The license_name and license_link fields are removed as apache-2.0 is a standard SPDX identifier.
Adding the paper title as a prominent header and a block of essential links (Paper, Code, Documentation, HF Collection, HF Demo, Discord) at the top of the model card, below the main image, for quick and easy access to key resources.
Updating the license entry within the "Model Details" section to "Apache 2.0" for consistency.

Improve model card: Add pipeline tag, correct license, and enhance linksc110ccc7

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