README.md

metadata

license: mit

---

language: en license: apache-2.0

My BERT Model

This is a BERT model fine-tuned for extracting embeddings from CVs and startup descriptions for matching purposes.

Model Details

• Architecture: BERT-base-uncased
• Use case: CV and Startup matching
• Training data: Not applicable (pre-trained model used)

How to use

from transformers import BertTokenizer, BertModel

tokenizer = BertTokenizer.from_pretrained("your_username/your_model_name")
model = BertModel.from_pretrained("your_username/your_model_name")

text = "Sample text"
inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
outputs = model(**inputs)
embedding = outputs.last_hidden_state.mean(dim=1).detach().numpy()