vecum0814/Cosmos3-Nano-LIBERO10-SFT
robotics model by vecum0814
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
A community fine-tune of NVIDIA Cosmos3-Nano for LIBERO-10, also called LIBERO-Long. The model jointly predicts robot action chunks and future video from camera observations and a task instruction. This is not an official NVIDIA checkpoint. This repository contains the frozen SFT policy used in our LIBERO evaluations. No optimism-based reinforcement learning or correction training has been applied to these weights. The seven BF16 model shards are approximately 31.5 GB. The included Wan2.2 video VAE adds approximately 2.82 GB. Both the Qwen vision encoder and the tokenizer/processor are already included. No separate Qwen language-model checkpoint is required for the supplied inference entry point. Use Linux, an NVIDIA GPU, and a compatible Cosmos Framework environment. The release uses: Set up the pinned framework using its installation instructions: With that environment active, start the included server wrapper. Replace the model directory with the directory downloaded above: The wrapper resolves the VAE and processor…
Read the full model card ↗ · Preview checked 2026-11-19T08:02:08.279Z
Inside the original model card — Document outline
- Cosmos3-Nano-LIBERO10-SFT
- Download
- Run the policy
- Training provenance
- Evaluation
- Included components and provenance correction
- License and attribution
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
vecum0814/Cosmos3-Nano-LIBERO10-SFT is a robotics model repository published by vecum0814 on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- robotics
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 15,173,136,576
- Architecture
- Cosmos3OmniModel
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-06T06:22:25.000Z
- Last modified
- 2026-10-06T06:26:20.000Z
Compatibility and lineage
Reported languages: en
Reported base models: nvidia/Cosmos3-Nano
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-06T06:39:56.505Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
1977kantomoyuki/act_so101_test_20260920_143445
abdulrahimmirani/pi05-piperx-pick-cube-ft01-simdata