Instructions to use tiiuae/Falcon3-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/Falcon3-7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="tiiuae/Falcon3-7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/Falcon3-7B-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("tiiuae/Falcon3-7B-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 Settings

vLLM

How to use tiiuae/Falcon3-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/Falcon3-7B-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/Falcon3-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiiuae/Falcon3-7B-Instruct

SGLang

How to use tiiuae/Falcon3-7B-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/Falcon3-7B-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/Falcon3-7B-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/Falcon3-7B-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/Falcon3-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiiuae/Falcon3-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/tiiuae/Falcon3-7B-Instruct
```

Issue Loading Tokenizer with Falcon 7B

by MRamiBen - opened Jan 7, 2025

Discussion

MRamiBen

Jan 7, 2025

Hello everyone,

I'm trying to load a tokenizer using the following command:

tokenizer = AutoTokenizer.from_pretrained("tiiuae/Falcon3-7B-Instruct")

However, I'm encountering this error:

Click to expand the error traceback


---------------------------------------------------------------------------  
Exception                                 Traceback (most recent call last)  
Cell In[23], line 1  
----> 1 tokenizer = AutoTokenizer.from_pretrained("tiiuae/Falcon3-7B-Instruct")   

File ~/GenAI/augmented_claims_manager/.venv/lib/python3.9/site-packages/transformers/models/auto/tokenization_auto.py:862, in AutoTokenizer.from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs)  
    858     if tokenizer_class is None:  
    859         raise ValueError(  
    860             f"Tokenizer class {tokenizer_class_candidate} does not exist or is not currently imported."  
    861         )  
--> 862     return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)  

... (truncated for brevity) ...

Exception: data did not match any variant of untagged enum ModelWrapper at line 664575 column 3

Has anyone encountered this issue before? Any guidance or suggestions on how to resolve it would be greatly appreciated. Thank you! 🙏

ybelkada

Technology Innovation Institute org Jan 7, 2025

Hi @MRamiBen
Can you try to update tokenizers library and run again your code ? pip install -U tokenizers

MRamiBen

Jan 8, 2025

Thank you for your response!
my tokenizers library was on version 0.19. After updating it to version 0.21, the issue has been resolved

puneeshkhanna changed discussion status to closed Apr 13, 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