Instructions to use osunlp/TableLlama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use osunlp/TableLlama with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="osunlp/TableLlama")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("osunlp/TableLlama") model = AutoModelForCausalLM.from_pretrained("osunlp/TableLlama") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use osunlp/TableLlama with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "osunlp/TableLlama" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "osunlp/TableLlama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/osunlp/TableLlama
- SGLang
How to use osunlp/TableLlama 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 "osunlp/TableLlama" \ --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": "osunlp/TableLlama", "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 "osunlp/TableLlama" \ --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": "osunlp/TableLlama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use osunlp/TableLlama with Docker Model Runner:
docker model run hf.co/osunlp/TableLlama
Error message while downloading the model
I am trying to download the model on Google Colab with the following command:
"
Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("osunlp/TableLlama")
model = AutoModelForCausalLM.from_pretrained("osunlp/TableLlama")
"
However, I get the following error message:
"ValueError: Couldn't instantiate the backend tokenizer from one of:
(1) a tokenizers library serialization file,
(2) a slow tokenizer instance to convert or
(3) an equivalent slow tokenizer class to instantiate and convert.
You need to have sentencepiece installed to convert a slow tokenizer to a fast one."
transformers version: 4.35.2
I tried "transformers version: 4.35.2" this version. You can try to install sentencepiece package using "!pip install sentencepiece" on Colab.
I can download it by the following codes:
from transformers import AutoModel, AutoTokenizer
def download_model(model_name):
# Replace "model_name" with the specific model you want to download
model = AutoModel.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Save the model and tokenizer to a directory
model.save_pretrained('./model_directory/')
tokenizer.save_pretrained('./model_directory/')
if __name__ == "__main__":
model_name = "osunlp/TableLlama"
download_model(model_name)