Coma Model

This repository contains a custom model for feature extraction using the BART architecture. The model and tokenizer are hosted on Hugging Face, and the inference is integrated into a Glitch server for processing WhatsApp messages.

Files and Directories

model/
- config.json
- generation_config.json
- model.safetensors
tokenizer/
- merges.txt
- special_tokens_map.json
- tokenizer_config.json
- vocab.json
README.md: This file.

Getting Started

1. Set Up Hugging Face Model

Ensure all model and tokenizer files are correctly uploaded to your Hugging Face repository.

2. Environment Variables

Create a .env file in your Glitch project with the following content:

Downloads last month: 3

Safetensors

Model size

0.1B params

Tensor type

F32