chunked/nltk_chunking/model_doc_phi/chunk_34.txt

model = PhiForCausalLM.from_pretrained("microsoft/phi-1_5", torch_dtype=torch.float16, attn_implementation="flash_attention_2").to("cuda")
tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1_5")
feel free to change the prompt to your liking.