happyhappy-jun/gr00t-n1.6-mt60k-ds0175

GR00T N1.6 — RoboCasa365 MT 60k (DeepSpeed 0.17.5)

This is an independently trained mid-training (MT) checkpoint based on NVIDIA GR00T N1.6. It is not an official NVIDIA release or a target-task fine-tuned checkpoint.

Checkpoint identity

• Training run: n1d6_mt_rc365_human300_bsz128_60k_ds0175
• Checkpoint: checkpoint-60000 (60,000 optimizer updates)
• DeepSpeed generation: 0.17.5, from the corrected training environment
• Role: common starting point for subsequent target-task fine-tuning
• Source promotion-manifest SHA-256: 8e32b7ed3be1b87d82c3131cc8384303ceec78493ea99eeb0911fe79acc19348

The model files are copied byte-for-byte from that promoted checkpoint. No weights, normalization statistics, modality settings, or configuration values were changed for this upload. See publication_manifest.json for sizes and SHA-256 checksums of the published source files.

Contents

• Two sharded Safetensors weight files and their index
• config.json
• processor_config.json
• statistics.json (normalization statistics)
• embodiment_id.json

Optimizer, scheduler, RNG state, training logs, internal experiment configs and training datasets are not included. This is a model export for inference or starting a new fine-tuning run, not a complete optimizer-state resume bundle.

Download and compatibility

from huggingface_hub import snapshot_download

checkpoint_dir = snapshot_download("happyhappy-jun/gr00t-n1.6-mt60k-ds0175")

Use this directory with compatible Isaac-GR00T N1.6 model/processor code. The model type is Gr00tN1d6; ordinary Transformers AutoModel loading has not been validated. The processor references nvidia/Eagle-Block2A-2B-v2, which may require separate model access/download. The preserved processor includes a RoboCasa new_embodiment modality configuration; use the matching embodiment, camera/state/action conventions and normalization statistics.

Upload verification covers source checksum identity, Safetensors/index structure and Hub file integrity. It is not a new GPU inference or robot rollout evaluation. No task-success or safety-performance claim is made by this model card.

License and safety

The underlying model is subject to the NVIDIA noncommercial license linked by the upstream model card. A complete, unmodified copy is included as LICENSE.pdf. The license restricts use to noncommercial research or evaluation. Public availability does not remove those restrictions.

Attribution: NVIDIA Isaac GR00T N1.6 and its underlying components. This repository is an independent derivative checkpoint and is not endorsed by NVIDIA.

Validate in simulation and use appropriate robot safety controls before any physical deployment. Outputs are not guaranteed to be safe or correct.