Instructions to use GAIR/autoj-13b-GPTQ-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GAIR/autoj-13b-GPTQ-4bits with Transformers:

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

pipe = pipeline("text-generation", model="GAIR/autoj-13b-GPTQ-4bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GAIR/autoj-13b-GPTQ-4bits")
model = AutoModelForCausalLM.from_pretrained("GAIR/autoj-13b-GPTQ-4bits", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GAIR/autoj-13b-GPTQ-4bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GAIR/autoj-13b-GPTQ-4bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GAIR/autoj-13b-GPTQ-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GAIR/autoj-13b-GPTQ-4bits

SGLang

How to use GAIR/autoj-13b-GPTQ-4bits 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 "GAIR/autoj-13b-GPTQ-4bits" \
    --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": "GAIR/autoj-13b-GPTQ-4bits",
		"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 "GAIR/autoj-13b-GPTQ-4bits" \
        --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": "GAIR/autoj-13b-GPTQ-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GAIR/autoj-13b-GPTQ-4bits with Docker Model Runner:
```
docker model run hf.co/GAIR/autoj-13b-GPTQ-4bits
```

This is a GPTQ 4bits version of Auto-J-13B. We convert it using this script (by TheBroke).

To use the 4bits version of Auto-J, you need to install the following packages:

pip install safetensors
pip install transformers>=4.32.0 optimum>=1.12.0
pip install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/  # Use cu117 if on CUDA 11.7

It takes about 8GB VRAM to load this model, and we provide an example for using it in example_gptq4bits.py.

Note that the behaviours of the quantized model and the original one might be different.

Please refer to our github repo for more datails.

Downloads last month: 23

Safetensors

Model size

13B params

Tensor type

F32

I32

F16