qwen3-8b-dapo-fulltokens-creativity-step11

Qwen3-8B DAPO model trained on full tokens (Creativity dataset). Best checkpoint: step 11 (val ACC=0.796, Reward=0.7654)

Model Details

This model is fine-tuned using DAPO (Direct Alignment from Preference Optimization) on the Creativity dataset.

Training Details

• Base Model: Qwen/Qwen3-8B-Instruct
• Training Method: DAPO
• Dataset: Creativity (train/val split)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Echoandland/qwen3-8b-dapo-fulltokens-creativity-step11")
tokenizer = AutoTokenizer.from_pretrained("Echoandland/qwen3-8b-dapo-fulltokens-creativity-step11")

# Your code here