giakhuyendihoc/pimamba-l12-depth4-libero-nolora-fullvlm
0
PI-Mamba L12 Depth4 LIBERO no-LoRA fullVLM
30k-step LIBERO finetuned checkpoint for PI-Mamba L12 depth4 no-LoRA fullVLM.
Checkpoint
- OpenPI config:
pi05_mamba_tiny_early_ctxd12_gated_fullvlm_libero_5090 - Experiment:
icra_nolora_fullvlm_pimamba_l12_depth4_cosine5e5_5e6_b16_acc1_seed42 - Step:
30000 - Initializer:
pi05_base_pytorch - Adaptation: full executed VLM / full vision / full PI-Mamba action path, no LoRA
- Context: early VLM exit at layer 12, ctxD K=64, pooled gated conditioning
- Mamba action mixer: depth 4, width 512
- Training: batch 16, grad accumulation 1, seed 42
- LR schedule: cosine from
5e-5to5e-6over 30k steps - LIBERO eval: seed 7, 50 trials per task, 10 denoising steps
Files included:
model.safetensorsmetadata.ptassets/physical-intelligence/libero/norm_stats.json
LIBERO Results
Efficiency
Use
Use with the matching PI-Mamba/OpenPI code and config:
--config-name pi05_mamba_tiny_early_ctxd12_gated_fullvlm_libero_5090
--checkpoint-dir /path/to/checkpointThe checkpoint includes the LIBERO norm stats under assets/physical-intelligence/libero.
