Add image-to-image pipeline tag to metadata

README.md

@@ -1,13 +1,14 @@
 ---
+datasets:
+- ILSVRC/imagenet-1k
 license: apache-2.0
+pipeline_tag: image-to-image
 tags:
-  - GEAR
-  - tokenizer
-  - VQGAN
-  - image-generation
-  - autoregressive
-datasets:
-  - ILSVRC/imagenet-1k
+- GEAR
+- tokenizer
+- VQGAN
+- image-generation
+- autoregressive
 ---
 
 # GEAR — GEAR-VQ
@@ -56,7 +57,7 @@ standard LlamaGen backbone; train your own on a frozen GEAR tokenizer with the
 | LFQ-16 | [`Warmup-LFQ`](https://huggingface.co/BinLin203/Warmup-LFQ) · `lfq-with-gan.pt` | [`GEAR-LFQ`](https://huggingface.co/BinLin203/GEAR-LFQ) · `gear-lfq.pt` |
 | IBQ-16 | [`Warmup-IBQ`](https://huggingface.co/BinLin203/Warmup-IBQ) · `ibq-with-gan.pt` | [`GEAR-IBQ`](https://huggingface.co/BinLin203/GEAR-IBQ) · `gear-ibq.pt` |
 
-## Reconstruction quality (ImageNet val)
+<h2>Reconstruction quality (ImageNet val)</h2>
 
 The warm-up and end-to-end (GEAR) tokenizers both keep reconstruction performance on par
 with the original pretrained weights.
@@ -137,4 +138,4 @@ Built on [LlamaGen](https://github.com/FoundationVision/LlamaGen),
 [Open-MAGVIT2](https://github.com/TencentARC/SEED-Voken),
 [IBQ](https://github.com/TencentARC/SEED-Voken),
 [iFSQ / LlamaGen-REPA](https://github.com/Tencent-Hunyuan/iFSQ); evaluation harness
-adapted from [UniWorld](https://github.com/PKU-YuanGroup/UniWorld).
+adapted from [UniWorld](https://github.com/PKU-YuanGroup/UniWorld).