Instructions to use HeshamHaroon/falcon-rw-1b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HeshamHaroon/falcon-rw-1b-4bit with Transformers:

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

pipe = pipeline("text-generation", model="HeshamHaroon/falcon-rw-1b-4bit", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HeshamHaroon/falcon-rw-1b-4bit", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("HeshamHaroon/falcon-rw-1b-4bit", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HeshamHaroon/falcon-rw-1b-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HeshamHaroon/falcon-rw-1b-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HeshamHaroon/falcon-rw-1b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HeshamHaroon/falcon-rw-1b-4bit

SGLang

How to use HeshamHaroon/falcon-rw-1b-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 "HeshamHaroon/falcon-rw-1b-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": "HeshamHaroon/falcon-rw-1b-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 "HeshamHaroon/falcon-rw-1b-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": "HeshamHaroon/falcon-rw-1b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HeshamHaroon/falcon-rw-1b-4bit with Docker Model Runner:
```
docker model run hf.co/HeshamHaroon/falcon-rw-1b-4bit
```

GPTQ Algorithm with `auto-gptq` Integration

Model Description

The GPTQ algorithm, developed by Frantar et al., is designed to compress transformer-based language models into fewer bits with minimal performance degradation. The auto-gptq library, based on the GPTQ algorithm, has been seamlessly integrated into the 🤗 transformers, enabling users to load and work with models quantized using the GPTQ algorithm.

Features

Quantization: Compress transformer-based language models with minimal performance loss.
Integration with 🤗 transformers: Directly load models quantized with the GPTQ algorithm.
Flexibility: Offers two scenarios for users:
1. Quantize a language model from scratch.
2. Load a pre-quantized model from the 🤗 Hub.
Calibration: Uses model inference to calibrate the quantized weights, ensuring optimal performance.
Custom Dataset Support: Users can quantize models using either a supported dataset or a custom dataset.

Intended Use

This integration is intended for users who want to compress their transformer-based language models without significant performance loss. It's especially useful for deployment scenarios where model size is a constraint.

Limitations and Considerations

The quality of quantization may vary based on the dataset used for calibration. It's recommended to use a dataset closely related to the model's domain for best results.
While the GPTQ algorithm minimizes performance degradation, some loss in performance is expected, especially at lower bit quantizations.

Training Data

The GPTQ algorithm requires calibration data for optimal quantization. Users can either use supported datasets like "c4", "wikitext2", etc., or provide a custom dataset for calibration.

Evaluation Results

Performance after quantization may vary based on the dataset used for calibration and the bit precision chosen for quantization. It's recommended to evaluate the quantized model on relevant tasks to ensure it meets the desired performance criteria.

References

Frantar et al., "GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers"
AutoGPTQ GitHub Repository

Downloads last month: 3

Safetensors

Model size

1B params

Tensor type

I32

F16

GPTQ Algorithm with auto-gptq Integration