Text Generation
PEFT
TensorBoard
Safetensors
llama
lora
grpo
instruction-hierarchy
prompt-injection
conversational
Instructions to use Perfect7613/llama31-8b-ih-grpo-seed42 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Perfect7613/llama31-8b-ih-grpo-seed42 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct") model = PeftModel.from_pretrained(base_model, "Perfect7613/llama31-8b-ih-grpo-seed42") - Notebooks
- Google Colab
- Kaggle
Ctrl+K