olmo3-7b-grpo-weighted-mul-creativity-step6

Olmo3-7B trained with GRPO (Weighted Mul) on Creativity dataset. Checkpoint: step 6

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Echoandland/olmo3-7b-grpo-weighted-mul-creativity-step6")
tokenizer = AutoTokenizer.from_pretrained("Echoandland/olmo3-7b-grpo-weighted-mul-creativity-step6")