app.py

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Llama-2-70B-Chat-fp16")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-70B-Chat-fp16")
input_text =" hello how are you?"
inputs= tokenizer.encode(input_text, return_tensors='pt')
outputs= model.generate(inputs,max_length=50,num_return_sequences=5,temperature=0.7)
print("Generated Text")
for i, output in enumerate(outputs):
    print(f"{i}: {tokenizer.decode(output)}")