Push model using huggingface_hub.

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+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 +1,59 @@
+{
+  "base_image_size": 256,
+  "codebook_embed_dim": 32,
+  "codebook_l2_norm": true,
+  "codebook_show_usage": true,
+  "codebook_size": 8192,
+  "commit_loss_beta": 0.25,
+  "dec_cls_token": false,
+  "dec_drop_path_rate": 0.0,
+  "dec_patch_size": 16,
+  "dec_pretrained": false,
+  "dec_tuning_method": "full",
+  "dec_type": "vit",
+  "decoder_ch_mult": [
+    1,
+    1,
+    2,
+    2,
+    4
+  ],
+  "decoder_model": "vit_base_patch14_dinov2_movqv2",
+  "dropout_p": 0.0,
+  "enc_drop_path_rate": 0.0,
+  "enc_patch_size": 16,
+  "enc_pretrained": false,
+  "enc_token_drop": 0.0,
+  "enc_token_drop_max": 0.6,
+  "enc_tuning_method": "full",
+  "enc_type": "vit",
+  "encoder_ch_mult": [
+    1,
+    1,
+    2,
+    2,
+    4
+  ],
+  "encoder_model": "vit_base_patch14_dinov2.lvd142m",
+  "entropy_loss_ratio": 0.0,
+  "image_size": 256,
+  "kl_loss_weight": 1e-06,
+  "num_codebooks": 4,
+  "num_latent_tokens": 128,
+  "repa": false,
+  "repa_align": "repeat",
+  "repa_loss_weight": 0.1,
+  "repa_model": "vit_large_patch14_dinov2.lvd142m",
+  "repa_patch_size": 16,
+  "repa_proj_dim": 1024,
+  "rope_mixed": true,
+  "rope_theta": 10.0,
+  "tau": 0.07,
+  "to_pixel": "linear",
+  "use_ape": false,
+  "use_rope": true,
+  "vq_loss_ratio": 1.0,
+  "vq_mean": 0.0,
+  "vq_std": 1.0,
+  "z_channels": 256
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98c01392ae0a7c0541eb1865c1efda65b81380bfecdd7a94e9537bec34ea9855
+size 695600328