HRM · Issues· 75 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #80
Full-Scale Experiment with exact_accuracy 0
Updated May 2, 2026 - #63
Question about carry state management across different samples during training
Updated Jan 17, 2026 - #10
arcprize.org leaderboard
Updated Jan 13, 2026 - #106
Question about baseline CoT prompts and settings (o3-mini-high, DeepSeek R1, Claude 3.7 8K)
Updated Jan 8, 2026 - #82
Reproducibility results of Sudoku-Extreme-1k
Updated Jan 7, 2026 - #104
How to use checkpoints tp predict?
Updated Dec 26, 2025 - #101
Replace bare except with explicit exception in model loading (evaluate.py)
Updated Dec 23, 2025 - #100
Is HRM suitable for text reasoning tasks on DNA sequences?
Updated Dec 18, 2025 - #98
not an issue but a fork
Updated Dec 4, 2025 - #41
import adam_atan2_backend ModuleNotFoundError: No module named 'adam_atan2_backend'
Updated Nov 30, 2025 - #97
Truc
Updated Nov 8, 2025 - #25
pip install adam_atan2 success then run code get No module named 'adam_atan2_backend'
Updated Nov 1, 2025 - #67
I would like to ask the model parameter 27, why does checkpoint have 2.2G?
Updated Oct 31, 2025 - #53
Universal Device Support Implementation
Updated Oct 17, 2025 - #90
Has anyone managed to run evaluate.py with the provided ARC-AGI-2 checkpoint?
Updated Oct 16, 2025