Text Generation
Transformers
PyTorch
Arabic
English
jais
Arabic
English
LLM
Decoder
causal-lm
custom_code
Instructions to use inceptionai/jais-13b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use inceptionai/jais-13b-chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="inceptionai/jais-13b-chat", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("inceptionai/jais-13b-chat", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use inceptionai/jais-13b-chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "inceptionai/jais-13b-chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "inceptionai/jais-13b-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/inceptionai/jais-13b-chat
- SGLang
How to use inceptionai/jais-13b-chat 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 "inceptionai/jais-13b-chat" \ --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": "inceptionai/jais-13b-chat", "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 "inceptionai/jais-13b-chat" \ --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": "inceptionai/jais-13b-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use inceptionai/jais-13b-chat with Docker Model Runner:
docker model run hf.co/inceptionai/jais-13b-chat
Runtime Error
#28
by prudhvi95 - opened
I am getting the following error when running jais on a large input text. Below is the code. What is the maximum context length for Jais-13b?
Error: The size of tensor a (2048) must match the size of tensor b (2049) at non-singleton dimension 3/
generate_ids = model.generate(
inputs,
top_p=0.9,
temperature=0.3,
max_new_tokens=1024,
min_length=input_len + 4,
repetition_penalty=1.2,
do_sample=True,
)
for JAIS-13B and JAIS-30B-v1 it is 2048. for JAIS-30B-v3 it is 8192. it says so in the whitepaper