Instructions to use tiiuae/Falcon3-3B-Instruct-1.58bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/Falcon3-3B-Instruct-1.58bit with Transformers:

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

pipe = pipeline("text-generation", model="tiiuae/Falcon3-3B-Instruct-1.58bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/Falcon3-3B-Instruct-1.58bit")
model = AutoModelForCausalLM.from_pretrained("tiiuae/Falcon3-3B-Instruct-1.58bit", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiiuae/Falcon3-3B-Instruct-1.58bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/Falcon3-3B-Instruct-1.58bit"
# 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/Falcon3-3B-Instruct-1.58bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiiuae/Falcon3-3B-Instruct-1.58bit

SGLang

How to use tiiuae/Falcon3-3B-Instruct-1.58bit 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/Falcon3-3B-Instruct-1.58bit" \
    --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/Falcon3-3B-Instruct-1.58bit",
		"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/Falcon3-3B-Instruct-1.58bit" \
        --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/Falcon3-3B-Instruct-1.58bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiiuae/Falcon3-3B-Instruct-1.58bit with Docker Model Runner:
```
docker model run hf.co/tiiuae/Falcon3-3B-Instruct-1.58bit
```

Falcon3-3B-Instruct-1.58bit

Commit History

(fix): align quantized models tokenizers with un-quantized ones (#4)

ff136ed
verified

ybelkada HF Staff commited on Jan 13, 2025

Update README.md

4cd316a
verified

ybelkada HF Staff commited on Dec 20, 2024

Upload tokenizer

c23b9a0
verified

ybelkada HF Staff commited on Dec 18, 2024

Update README.md (#3)

ad7da73
verified

puneeshkhanna

hangzou commited on Dec 18, 2024

Update README.md (#2)

d78ec48
verified

ybelkada HF Staff

hangzou commited on Dec 18, 2024

Update README.md (#1)

37b3b2b
verified

ybelkada HF Staff

hangzou commited on Dec 18, 2024

falcon3 release

d5fe544

slim.frikha commited on Dec 17, 2024

Commit History

(fix): align quantized models tokenizers with un-quantized ones (#4) ff136ed verified

Update README.md 4cd316a verified

Upload tokenizer c23b9a0 verified

Update README.md (#3) ad7da73 verified

Update README.md (#2) d78ec48 verified

Update README.md (#1) 37b3b2b verified

falcon3 release d5fe544

(fix): align quantized models tokenizers with un-quantized ones (#4)

ff136ed
verified

Update README.md

4cd316a
verified

Upload tokenizer

c23b9a0
verified

Update README.md (#3)

ad7da73
verified

Update README.md (#2)

d78ec48
verified

Update README.md (#1)

37b3b2b
verified

falcon3 release

d5fe544