app.py

import os
from huggingface_hub import InferenceClient, login
from transformers import AutoTokenizer
from langchain.chat_models import ChatOpenAI

# access token with permission to access the model and PRO subscription
hf_token = "YOUR_HF_TOKEN" # <https://huggingface.co/settings/tokens>
login(token=hf_token)

# tokenizer for generating prompt
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-70b-chat-hf")

# inference client
client = InferenceClient("https://api-inference.huggingface.co/models/meta-llama/Llama-2-70b-chat-hf")

# generate function
def generate(text):
    payload = tokenizer.apply_chat_template([{"role":"user","content":text}],tokenize=False)
    res = client.text_generation(
                    payload,
                    do_sample=True,
                    return_full_text=False,
                    max_new_tokens=2048,
                    top_p=0.9,
                    temperature=0.6,
                )
    return res.strip()

# test client
assert generate("What is 2+2?") == "The answer to 2+2 is 4."

# create evaluator
os.environ["OPENAI_API_KEY"] = "YOUR_OPENAI_API_KEY" # https://platform.openai.com/account/api-keys
assert os.environ.get("OPENAI_API_KEY") is not None, "Please set OPENAI_API_KEY environment variable"

evaluation_llm = ChatOpenAI(model="gpt-4")