Push model using huggingface_hub.
Browse files- README.md +12 -0
- config.json +41 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- arxiv:2501.07730
|
| 5 |
+
- model_hub_mixin
|
| 6 |
+
- pytorch_model_hub_mixin
|
| 7 |
+
- text-to-image-generation
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
| 11 |
+
- Library: https://github.com/bytedance/1d-tokenizer
|
| 12 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"experiment": {
|
| 3 |
+
"tokenizer_checkpoint": "tatitok_bl128_vq.bin",
|
| 4 |
+
"generator_checkpoint": "maskgen_vq_l.bin"
|
| 5 |
+
},
|
| 6 |
+
"model": {
|
| 7 |
+
"vq_model": {
|
| 8 |
+
"quantize_mode": "vq",
|
| 9 |
+
"codebook_size": 8192,
|
| 10 |
+
"token_size": 64,
|
| 11 |
+
"use_l2_norm": false,
|
| 12 |
+
"commitment_cost": 0.25,
|
| 13 |
+
"clustering_vq": false,
|
| 14 |
+
"vit_enc_model_size": "base",
|
| 15 |
+
"vit_dec_model_size": "large",
|
| 16 |
+
"vit_enc_patch_size": 16,
|
| 17 |
+
"vit_dec_patch_size": 16,
|
| 18 |
+
"num_latent_tokens": 128,
|
| 19 |
+
"finetune_decoder": false,
|
| 20 |
+
"is_legacy": false
|
| 21 |
+
},
|
| 22 |
+
"maskgen": {
|
| 23 |
+
"decoder_embed_dim": 1024,
|
| 24 |
+
"decoder_depth": 16,
|
| 25 |
+
"decoder_num_heads": 16,
|
| 26 |
+
"micro_condition": true,
|
| 27 |
+
"micro_condition_embed_dim": 256,
|
| 28 |
+
"text_drop_prob": 0.1,
|
| 29 |
+
"condition_num_classes": 1000,
|
| 30 |
+
"cfg": 12.0,
|
| 31 |
+
"num_iter": 16,
|
| 32 |
+
"temperature": 2.0,
|
| 33 |
+
"sample_aesthetic_score": 6.5
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"dataset": {
|
| 37 |
+
"preprocessing": {
|
| 38 |
+
"crop_size": 256
|
| 39 |
+
}
|
| 40 |
+
}
|
| 41 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7021e110ee7d28fe34da72abcce6aa8f882d23f50d978bc7a41b95a2fed568d3
|
| 3 |
+
size 2417292712
|