Instructions to use LLMSafety/Falcon3-7B-Base-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLMSafety/Falcon3-7B-Base-4bit with Transformers:

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

pipe = pipeline("text-generation", model="LLMSafety/Falcon3-7B-Base-4bit")

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

tokenizer = AutoTokenizer.from_pretrained("LLMSafety/Falcon3-7B-Base-4bit")
model = AutoModelForCausalLM.from_pretrained("LLMSafety/Falcon3-7B-Base-4bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LLMSafety/Falcon3-7B-Base-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLMSafety/Falcon3-7B-Base-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLMSafety/Falcon3-7B-Base-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LLMSafety/Falcon3-7B-Base-4bit

SGLang

How to use LLMSafety/Falcon3-7B-Base-4bit 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 "LLMSafety/Falcon3-7B-Base-4bit" \
    --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": "LLMSafety/Falcon3-7B-Base-4bit",
		"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 "LLMSafety/Falcon3-7B-Base-4bit" \
        --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": "LLMSafety/Falcon3-7B-Base-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LLMSafety/Falcon3-7B-Base-4bit with Docker Model Runner:
```
docker model run hf.co/LLMSafety/Falcon3-7B-Base-4bit
```

Falcon3-7B-Base-4bit

File size: 755 Bytes

e02e121

{
  "add_prefix_space": false,
  "backend": "tokenizers",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "extra_special_tokens": [
    ">>TITLE<<",
    ">>ABSTRACT<<",
    ">>INTRODUCTION<<",
    ">>SUMMARY<<",
    ">>COMMENT<<",
    ">>ANSWER<<",
    ">>QUESTION<<",
    ">>DOMAIN<<",
    ">>EMAIL_ADDRESS<<",
    ">>IP_ADDRESS<<",
    "<|startoftext|>",
    ">>IP_ADDRESS_0<<",
    ">>IP_ADDRESS_1<<",
    ">>IP_ADDRESS_2<<",
    ">>IP_ADDRESS_3<<",
    ">>IP_ADDRESS_4<<",
    ">>IP_ADDRESS_5<<",
    ">>IP_ADDRESS_6<<",
    ">>IP_ADDRESS_7<<",
    ">>IP_ADDRESS_8<<",
    ">>IP_ADDRESS_9<<",
    ">>PASSWORD<<",
    ">>KEY<<"
  ],
  "is_local": false,
  "model_max_length": 32768,
  "tokenizer_class": "TokenizersBackend"
}