My implementation for the AutoModel AutoTokenizer classes are fairly simple:

`from transformers import AutoModel, AutoTokenizer
import numpy as np
from rank_bm25 import BM25Okapi
from sklearn.neighbors import NearestNeighbors

class EmbeddingModels:

def bert(self, model_name, text):
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModel.from_pretrained(model_name)
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
    outputs = model(**inputs)
    embeddings = outputs.last_hidden_state.mean(dim=1).detach().numpy()
    return embeddings

def create_chunks(self, text, chunk_size):
    return [text[i:i + chunk_size] for i in range(0, len(text), chunk_size)]`

But I can’t get this warning to go away:

A parameter name that contains 'beta' will be renamed internally to 'bias'. Please use a different name to suppress this warning. A parameter name that contains 'gamma' will be renamed internally to 'weight'. Please use a different name to suppress this warning.

There is no reference to the word beta or gamma anywhere in my repo.

Updating the package, suppressing the warnings with import warnings