metadata
license: mit
datasets: pt-sk/toxic_classification
tags:
- PPO
- RLHF
pipeline_tag: text-generation
Aligning the model using Proximal Policy Optimization (PPO). The goal is to train the model to generate non-toxic reviews. The training process utilizes the trl library for reinforcement learning, the transformers library for model handling, and datasets for dataset management.
Implementation code is available here: GitHub
# Load model and tokenizer directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("pt-sk/GPT2_NonToxic")
model = AutoModelForCausalLM.from_pretrained("pt-sk/GPT2_NonToxic")
# Example usage
input_text = "The movie was fantastic"
inputs = tokenizer(input_text, return_tensors='pt')
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))