Downloads · 30 days
0
TTianCheng/cole-p2-alfworld-rloo-wm-qwen2.5-1.5b-seed0
cole-p2-alfworld-rloo-wm-qwen2.5-1.5b-seed0 is a reinforcement learning model from TTianCheng. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Final step-150 training checkpoint for the P2 run (seed 0). Final ALFWorld success rate: 0.8203125; test score: 5.7360029663.
Downloads · 30 days
0
Access
Public
Updated Sep 24, 2026
Repo size
19.5 GB
Likes
0
Public
Click a slice to open those files.
.pt19.5 GB · 100%
From the Hugging Face model README
Final step-150 training checkpoint for the P2 run (seed 0). Final ALFWorld success rate: 0.8203125; test score: 5.7360029663.
manifest.json records every checkpoint file's byte size and SHA-256.