hubnemo/Qwen3-8B-ALoRA-MTP-60k-was-80k-skip-prefix-40k-rand-dataset-loss_decay Updated about 10 hours ago
hubnemo/Qwen3-8B-ALoRA-MTP-60k-skip-prefix-40k-rand-dataset-loss_decay-r32-lc1 Updated about 16 hours ago
hubnemo/Qwen3-8B-ALoRA-MTP-100k-skip-prefix-dataset-conversational-loss_decay Updated about 18 hours ago
hubnemo/so101_smolvla_exp10_bs16_steps20k_r32_warmup_ema-ema Robotics • 0.5B • Updated 11 days ago • 20