vibhorg
/

rl4llm_uofm_nlpo_super_t5_arxiv

Text2Text Generation

Transformers

PyTorch

English

text-generation-inference

rlhf

PPO

Inference Endpoints

Model card Files Files and versions Community

Edit model card

This model is fintuned using PPO based NLPO RL algorithm, on ccdv/arxiv-summarization dataset. The base model is pretunerd version of flan-t5-base model.

Downloads last month: 1

Dataset used to train vibhorg/rl4llm_uofm_nlpo_super_t5_arxiv