from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("StanfordAIMI/RadLLaMA-7b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("StanfordAIMI/RadLLaMA-7b")

prompt = "Hi"
conv = [{"from": "human", "value": prompt}]
input_ids = tokenizer.apply_chat_template(conv, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(input_ids)
response = tokenizer.decode(outputs[0])
print(response)

✏️ Citation

@article{aimifms-2024,
  title={},
  author={},
  journal={arXiv preprint arXiv:xxxx.xxxxx},
  url={https://arxiv.org/abs/xxxx.xxxxx},
  year={2024}
}