Instructions to use inception42/jais-30b-chat-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inception42/jais-30b-chat-v1 with Transformers:

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

pipe = pipeline("text-generation", model="inception42/jais-30b-chat-v1", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("inception42/jais-30b-chat-v1", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inception42/jais-30b-chat-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inception42/jais-30b-chat-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inception42/jais-30b-chat-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/inception42/jais-30b-chat-v1

SGLang

How to use inception42/jais-30b-chat-v1 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 "inception42/jais-30b-chat-v1" \
    --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": "inception42/jais-30b-chat-v1",
		"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 "inception42/jais-30b-chat-v1" \
        --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": "inception42/jais-30b-chat-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use inception42/jais-30b-chat-v1 with Docker Model Runner:
```
docker model run hf.co/inception42/jais-30b-chat-v1
```

Model inference speed ....

by halsayed - opened Nov 16, 2023

Discussion

halsayed

Nov 16, 2023

Hi Core42 team,

Thanks for creating this opensource arabic model. I tested the model based on the provided example on the model card and I got very slow performance. I'm using A100 80GB, so I would expect a much better performance than the results shown on the image below. is this correct?

samta-kamboj

Inception42 org Nov 17, 2023

@halsayed Thanks for using Jais. You may get better inference speed using 2 x A100 80GB GPUs as the model size is ~(30x4)GB and all layers of the model could fit on 2 GPUs.

halsayed

Nov 17, 2023

@samta-kamboj thanks, increasing GPU solved the problem. Was there any attempt to quantize the model and reduce the vram footprint?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment