Reinforcement Learning
Transformers
Safetensors
gpt2
text-generation
trl
ppo
text-generation-inference
Instructions to use LouisSanna/hw2-ppo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LouisSanna/hw2-ppo with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LouisSanna/hw2-ppo") model = AutoModelForCausalLM.from_pretrained("LouisSanna/hw2-ppo") - Notebooks
- Google Colab
- Kaggle