Instructions to use twhoool02/Falcon-7B-instruct-NF4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use twhoool02/Falcon-7B-instruct-NF4 with Transformers:

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

pipe = pipeline("text-generation", model="twhoool02/Falcon-7B-instruct-NF4", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("twhoool02/Falcon-7B-instruct-NF4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("twhoool02/Falcon-7B-instruct-NF4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use twhoool02/Falcon-7B-instruct-NF4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "twhoool02/Falcon-7B-instruct-NF4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "twhoool02/Falcon-7B-instruct-NF4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/twhoool02/Falcon-7B-instruct-NF4

SGLang

How to use twhoool02/Falcon-7B-instruct-NF4 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 "twhoool02/Falcon-7B-instruct-NF4" \
    --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": "twhoool02/Falcon-7B-instruct-NF4",
		"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 "twhoool02/Falcon-7B-instruct-NF4" \
        --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": "twhoool02/Falcon-7B-instruct-NF4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use twhoool02/Falcon-7B-instruct-NF4 with Docker Model Runner:
```
docker model run hf.co/twhoool02/Falcon-7B-instruct-NF4
```

Model Card for Falcon-7B-instruct-NF4

Model Details

This model is a NF4 quantized version of the tiiuae/falcon-7b-instruct model.

Developed by: Ted Whooley
Library: Transformers, NF4
Model type: falcon
Model name: Falcon-7B-instruct-NF4
Pipeline tag: text-generation
Qunatized by: twhoool02
Language(s) (NLP): en
License: other

Downloads last month: 5

Safetensors

Model size

7B params

Tensor type

F32

F16

Model tree for twhoool02/Falcon-7B-instruct-NF4

Base model

tiiuae/falcon-7b-instruct

Quantized

(16)

this model