metadata

library_name: transformers
tags: []

Model Card for Model ID

Model Details

Vinallama 2.7B Model for Harmful Information Refusal

This project involves training the Vinallama 2.7B model to effectively refuse to provide harmful or sensitive information. By fine-tuning the model on specific datasets, we aim to enhance its ability to identify and reject potentially dangerous content, ensuring safer interactions and protecting users from misinformation and malicious content.

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: Duong Trong Chi
Language(s) (NLP): VietNam
Finetuned from model [optional]: Vinallama-2.7b-chat

Model Card Contact

My email: duongtrongchi.work@gmail.com