Downloads · 30 days
318
100% of all-time downloads
wam_ctxpool_mimonly
hmkang/wam_ctxpool_mimonly
wam_ctxpool_mimonly is a robotics model from hmkang. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for wan2.2. The card lists the license as apache-2.0.
Wan2.2 TI2V-5B video DiT + DiT-B action head, V2V-student, iBOT MIM-only (WAMFADISTILLIBOTL1=0 — the CLS/DINO term is off, the per-token prototype-CE is the whole representation loss), two independent moderate-aug dra…
All-time downloads
318
Public
Repo size
394 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors394 GB · 100%
At a glance
- Task
- Robotics
- Library
- wan2.2
- License
- apache-2.0
- Access
- Public
- Created
- Sep 19, 2026
- Updated
- Sep 21, 2026
- SHA
- 37ec3bea
Model card
From the Hugging Face model README
WAM DiT4DiT — context pooling on the MIM-only recipe (RoboCasa-300)
Wan2.2 TI2V-5B video DiT + DiT-B action head, V2V-student, iBOT MIM-only
(WAM_FADISTILL_IBOT_L1=0 — the CLS/DINO term is off, the per-token prototype-CE is the whole
representation loss), two independent moderate-aug draws per clip.
| folder | pooling | history |
|---|---|---|
control_hist9/ | none | hist9 (nin 17 / nout 33, fdf 2) |
xattn_ffn_L3_hist9/ | cross-attn + FFN at L3 | hist9 |
avg_L3_hist9/ | average at L3 | hist9 |
xattn_ffn_L3_hist13/ | cross-attn + FFN at L3 | hist13 (nin 25 / nout 41) |
Plate: 4 GPU x per-device 8, no gradient accumulation, 100k steps, 256 tmosaic (3 views). Uploaded on a 20k grid. Optimizer state, RNG and scheduler are not included.
- Task
- Robotics
- Library
- wan2.2
- License
- apache-2.0
- Created
- Sep 19, 2026
- Updated
- Sep 21, 2026