Hugging Face's logo

mwitiderrick
/
opt-125-imdb-ppo

Text Generation
Transformers
Safetensors
opt
text-generation-inference
Inference Endpoints
Model card Files Community
opt-125-imdb-ppo / README.md
mwitiderrick's picture
mwitiderrick
Update README.md
6293cb8 verified
preview code
|
raw
history blame contribute delete
No virus
426 Bytes
metadata
library_name: transformers
tags: []

Model Card for Model ID

We fine-tune OPT-125 to generate positive movie reviews based on the IMDB dataset. The model gets the start of a real review and is tasked to produce positive continuations. To reward positive continuations we use a BERT classifier to analyse the sentiment of the produced sentences and use the classifier's outputs as rewards signals for PPO training