How to run the model ?

Load base model

model = AutoModelForCausalLM.from_pretrained( "Tapan101/Llama-2-7b-Medical-chat-finetune" )

Load LLaMA tokenizer

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True) tokenizer.pad_token = tokenizer.eos_token tokenizer.padding_side = "right" # Fix weird overflow issue with fp16 training

import logging from transformers import pipeline

Suppress warning messages

logging.getLogger("transformers.generation_utils").setLevel(logging.ERROR)

Run text generation pipeline with our next model

prompt = "What is dance therapy ?" #How does dysmenorrhea is diagnosised through allopathic pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200) result = pipe(f"~~[INST] {prompt} [/INST]") generated_text = result[0] print(generated_text)~~