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

Libraries

How to use haouarin/jais-13b-chat-GPTQ-4bits with Transformers:

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

pipe = pipeline("text-generation", model="haouarin/jais-13b-chat-GPTQ-4bits", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("haouarin/jais-13b-chat-GPTQ-4bits", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use haouarin/jais-13b-chat-GPTQ-4bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "haouarin/jais-13b-chat-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": "haouarin/jais-13b-chat-GPTQ-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/haouarin/jais-13b-chat-GPTQ-4bits

SGLang

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

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

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

This is the quantized version 4-bits created using autotrain, but it doesn't work.

Error

GPU

CPU

Quantization Process

!pip install auto-gptq
!pip install git+https://github.com/huggingface/optimum.git
!pip install git+https://github.com/huggingface/transformers.git
!pip install --upgrade accelerate

from transformers import AutoModelForCausalLM, AutoTokenizer,GPTQConfig
tokenizer = AutoTokenizer.from_pretrained("inception-mbzuai/jais-13b-chat")
gptq_config = GPTQConfig(bits=4, dataset = "c4", tokenizer=tokenizer)
model = AutoModelForCausalLM.from_pretrained('inception-mbzuai/jais-13b-chat', quantization_config=gptq_config,trust_remote_code=True)

Downloads last month: 6