Rehost Sapiens normal 0.3B as safetensors
Browse files- README.md +18 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
library_name: sceneworks
|
| 4 |
+
base_model: facebook/sapiens-normal-0.3b
|
| 5 |
+
tags: [sapiens, surface-normals]
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# Sapiens normal 0.3B (SceneWorks safetensors rehost)
|
| 9 |
+
|
| 10 |
+
Safetensors re-container of Meta's Sapiens surface-normal 0.3B checkpoint, used by SceneWorks' MLX and Candle trainers for the frozen, differentiable surface-normal loss in character LoRA training.
|
| 11 |
+
|
| 12 |
+
## Provenance
|
| 13 |
+
- Source: [facebook/sapiens-normal-0.3b](https://huggingface.co/facebook/sapiens-normal-0.3b) at revision `ada60522133d083464e5b70172adab7568ce6f49`, file `sapiens_0.3b_normal_render_people_epoch_66.pth`.
|
| 14 |
+
- Source sha256: `47792bbed2d3ea7537970230d5c6c7fb2b45c89bac384435bfbd6b2db03efb61` (1,358,042,350 bytes).
|
| 15 |
+
- License: CC-BY-NC-4.0, inherited from the source (non-commercial use only). Attribution: Meta Platforms, "Sapiens: Foundation for Human Vision Models".
|
| 16 |
+
- Conversion: `torch.load(weights_only=True)` → the `state_dict` tensors saved with `safetensors.torch.save_file`, keys UNCHANGED (`backbone.*`, `decode_head.*`); no tensor renamed, cast or dropped (the non-tensor `meta` entry is omitted). 304 tensors. Equivalent to `scripts/reference/body_losses_reference.py --convert` in the SceneWorks inference repo.
|
| 17 |
+
|
| 18 |
+
`model.safetensors` sha256: `b37670417447b6da441111e0c950bf9e694bf92777616d81ee72b82d2f9387fc`
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b37670417447b6da441111e0c950bf9e694bf92777616d81ee72b82d2f9387fc
|
| 3 |
+
size 1357935996
|