qwen3-8b-dapo-high-entropy-step2

Qwen3-8B DAPO model trained on top-20% high-entropy tokens only (Creativity dataset). Checkpoint: step 2 (val ACC=0.796, Reward=0.7637)

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-high-entropy-step2")
tokenizer = AutoTokenizer.from_pretrained("Echoandland/qwen3-8b-dapo-high-entropy-step2")

# Your code here