Push model using huggingface_hub.

README.md

@@ -1,12 +1,9 @@
 ---
 tags:
-- video-to-3d
+- model_hub_mixin
+- pytorch_model_hub_mixin
 ---
 
-SLAM3R is a real-time RGB SLAM system that performs dense 3D reconstruction via points regression with feed-forward neural networks.
-
-This repository contains pre-trained weights for the Image-to-Points network, which converts short video clips into dense point clouds with all frames aligned in a unified coordinate system. 
-
-Paper: https://huggingface.co/papers/2412.09401
-
-Code: https://github.com/PKU-VCL-3DV/SLAM3R
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

config.json

@@ -0,0 +1,29 @@
+{
+  "conf_mode": [
+    "exp",
+    1,
+    Infinity
+  ],
+  "corr_depth": 2,
+  "dec_depth": 12,
+  "dec_embed_dim": 768,
+  "dec_num_heads": 12,
+  "depth_mode": [
+    "exp",
+    -Infinity,
+    Infinity
+  ],
+  "enc_depth": 24,
+  "enc_embed_dim": 1024,
+  "enc_minibatch": 11,
+  "enc_num_heads": 16,
+  "head_type": "linear",
+  "img_size": [
+    224,
+    224
+  ],
+  "mv_dec1": "MultiviewDecoderBlock_max",
+  "mv_dec2": "MultiviewDecoderBlock_max",
+  "output_mode": "pts3d",
+  "pos_embed": "RoPE100"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f58b4a39f9e3641ed2fe19d16a82be956975ec1ecb568899c8852370aa78b8c
+size 2131831108