Downloads · 30 days
4
9% of all-time downloads
vpraise00/smolvla-raise-med-pill-sfvlm-curriculum-100ep-14d-5ep-bs32
smolvla-raise-med-pill-sfvlm-curriculum-100ep-14d-5ep-bs32 is a machine learning model from vpraise00. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for lerobot. The card lists the license as apache-2.0.
Recovered 5-epoch SmolVLA checkpoint for the RAISE insertpillintoopenbottle curriculum recipe.
Downloads · 30 days
4
9% of all-time downloads
All-time downloads
47
Public
Parameters
450M
907 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors907 MB · 100%
How the weights are stored.
BF16447M · 99%
From the Hugging Face model README
Recovered 5-epoch SmolVLA checkpoint for the RAISE insert_pill_into_open_bottle curriculum recipe.
curriculum_35_30_20_10_5vpraise00/raise-medicine-insert-pill-sft5-statefix-vlmclean-curriculum-35-30-20-10-5-100ep-14d-trainmix925032/data/workspace/raise/results/runs/smolvla_insert_pill_statefix_vlmclean_14d_5ep_bs32_20260706_071232The training run reached the final checkpoint, then failed before Hugging Face upload during W&B model artifact logging because the generated artifact name exceeded W&B's length limit. The checkpoint weights were not modified for this recovery upload. See raise_artifacts/recovery_upload_manifest.json for details.