app.py

from transformers import AutoTokenizer
import transformers
import torch

model = "meta-llama/Llama-2-7b-chat-hf"

tokenizer = AutoTokenizer.from_pretrained(
    model,
    use_auth_token=True,
)

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

def gen(x, max_length=200):
    sequences = pipeline(
        x,
        do_sample=True,
        top_k=10,
        num_return_sequences=1,
        eos_token_id=tokenizer.eos_token_id,
        max_length=max_length,
    )

    return sequences[0]["generated_text"].replace(x, "")

print(gen('I liked "Breaking Bad" and "Band of Brothers". Do you have any recommendations of other shows I might like?\n'))