link :- https://colab.research.google.com/drive/1aAPjCM5FZH-Pi8rGHOMk8-UUYibwuSXn?usp=sharing

<!--

pip install transformers accelerate

from transformers import AutoTokenizer import transformers import torch

model = "hem007/Llama-2-7b-chat-finetune" prompt = "What is a deep learning?"

tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", )

sequences = pipeline( f'<s>[INST] {prompt} [/INST]', do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, max_length=200, ) for seq in sequences: print(f"Result: {seq['generated_text']}")

prompt="how to make pasta?" # user input sequences = pipeline( f'<s>[INST] {prompt} [/INST]', do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, max_length=400, ) for seq in sequences: print(f"Result: {seq['generated_text']}") -->