Spaces:
Sleeping
Apply for community grant: Academic project (gpu)
Project Description:
I am a graduate research assistant working on a project to generate high-quality article headlines using a fine-tuned large language model (LLM). The model has been trained using Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to optimize for engaging, relevant, and impactful headlines.
To share this work with the open-source community, I aim to deploy the model on Hugging Face Spaces so that journalists, content creators, and researchers can easily experiment with and benefit from it.
Why I Need the Grant:
My focus is solely on deployment. To ensure fast and smooth inference, I need access to a basic GPU for running the model efficiently. The grant would help make the model publicly accessible without high latency, allowing users to interact with it in real time.
How This Benefits the Open-Source Community:
Provides an easy-to-use demo for headline generation, benefiting content creators and researchers.
Supports open science by making a fine-tuned LLM available for real-world applications.
Encourages further exploration of SFT and DPO for text generation.
Helps others understand best practices for deploying fine-tuned models efficiently.