Downloads · 30 days
5
31% of all-time downloads
dreamdifferent/vam-cross-level5-panda-robotiq-widowx-texture-video-lora-iter400
vam-cross-level5-panda-robotiq-widowx-texture-video-lora-iter400 is a robotics model from dreamdifferent. Use it for the robotics task on the model card, and read the license before you ship it in a product.
This public repository contains the trainable-only Video2World LoRA checkpoint from iteration 400 of v2wpandarobotiqlevel5widowxtexture2camhstackfromwidowx250videofusedf0cea76lorar256. The source run has termination s…
Downloads · 30 days
5
31% of all-time downloads
All-time downloads
16
Public
Repo size
3.7 GB
Likes
0
Public
Click a slice to open those files.
.pt3.7 GB · 100%
From the Hugging Face model README
This public repository contains the trainable-only Video2World LoRA
checkpoint from iteration 400 of v2w_panda_robotiq_level5_widowx_texture_2cam_hstack_from_widowx250_video_fused_f0cea76_lora_r256.
The source run has termination status walltime;
the selected four-component checkpoint set was verified before selecting the
model weight.
fused_video2world_ditdreamdifferent/widowx250-video-fusedf0cea76b62c5dd66b06b9f965932ddea32a7b546checkpoints/video_backbone/iter_000001060_fused.ptd0f24c049bee63b03d3b62747b240a2d1822ddd5f83a52fcd866a882e80122b1This is an adapter checkpoint, not a standalone fused model. Load the exact
initial Video2World backbone above first and then apply this LoRA checkpoint.
For fused_video2world_dit, the initial checkpoint already includes the
earlier WidowX/Bridge LoRA fusion; loading the original Bridge backbone instead
would be incorrect.
e3355dbc93132b576c02f920a59b4fc18a4f5906jonpai/mimic-video@f28339034831e3c2374be075e622e1ff38ebe0f8video_backbone/tokenizer/tokenizer.pthtext_encoder/t5-11bUse the same MimicVideo code and config recorded in config.yaml,
vam_cross_video2world_config.json, and
vam_cross_video_lora_manifest.json.
dreamdifferent/vam-cross-level5-panda-robotiq-widowx-texture@9656f4f8132995788fb30e5b52b418787f528b04observation.images.corner_cam, observation.images.front_camhstack at 5 Hzpick up the candle and place it into the bowlThe dataset itself is not included. Users must comply with the dataset's current access policy and the upstream MimicVideo, NVIDIA Cosmos, and base-checkpoint terms.