bert_assurance

Model Description

This is the model card of an insurance embeddings model that has been trained on customer documentation with 50K datapoints.

• Developed by: Taymed
• Model type: BERT base finetuned
• Language(s) (NLP): Fr
• License: [Spellz ltd]
• Finetuned from model: [BERT base]

Model Sources [optional]

• Huggingface: [https://huggingface.co/google-bert/bert-base-uncased]

How to Get Started with the Model

from transformers import AutoTokenizer, AutoModel
import torch

# Define the model name (either your custom model or a pre-trained model from Hugging Face)
model_name = "ortaymed/bert_assurance"  # Replace with your model name or path

# Your Hugging Face token
hf_token = "your-huggingface-token"  # Replace with your actual Hugging Face token

# Load the tokenizer and model with the token
tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
model = AutoModel.from_pretrained(model_name, use_auth_token=hf_token)

# Sample input text
input_text = "Your sample input text goes here."

# Tokenize the input text
inputs = tokenizer(input_text, return_tensors="pt")

# Get embeddings
with torch.no_grad():
    outputs = model(**inputs)

# Get the embeddings from the last hidden state
embeddings = outputs.last_hidden_state

print(embeddings)