Add README with results table and download links

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+tags:
+  - vision
+  - image-classification
+  - ternary
+  - quantization
+  - vit
+datasets:
+  - imagenet-1k
+  - cifar10
+  - cifar100
+---
+
+# FTerViT: Fully Ternary Vision Transformer
+
+Pretrained checkpoints for **FTerViT** — the first fully ternary Vision Transformer where *all* weight matrices and normalization parameters are constrained to {-1, 0, +1}.
+
+**Paper:** [FTerViT: Fully Ternary Vision Transformer](https://arxiv.org/abs/XXXX.XXXXX) (NeurIPS 2026 submission)  
+**Code:** [github.com/szymonrucinski/FTerViT](https://github.com/szymonrucinski/FTerViT)
+
+## Key Results
+
+All models use **W2A8** (2-bit weights, 8-bit activations) with 100% ternary coverage — including patch embedding, LayerNorm, and classifier head.
+
+### ImageNet-1K
+
+| Model | Phase | Epochs | Top-1 (%) | Size (MB) | Compression | Checkpoint |
+|-------|-------|--------|-----------|-----------|-------------|------------|
+| DeiT-Small | Phase 1 | 250 | 75.05 | 5.81 | 15.2× | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase1_ep250_acc75.05_deit_small_224.pth) |
+| DeiT-III-Small | Phase 1 | 250 | 76.78 | 5.81 | 15.2× | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase1_ep250_acc76.78_deit3_small_224.pth) |
+| DeiT-Small | Phase 2 | +10 | **77.47** | 5.81 | 15.2× | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase2_ep010_acc77.47_deit_small_224.pth) |
+| DeiT-III-Small | Phase 2 | +10 | **79.64** | 5.81 | 15.2× | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase2_ep010_acc79.64_deit3_small_224.pth) |
+
+### CIFAR-10 / CIFAR-100
+
+| Model | Dataset | Top-1 (%) | FP32 Baseline | Size (MB) | Checkpoint |
+|-------|---------|-----------|---------------|-----------|------------|
+| DeiT-Tiny | CIFAR-10 | **97.43** | 97.52 | 1.53 | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/cifar10/phase2_ep010_acc97.43_deit_tiny_224.pth) |
+| DeiT-Tiny | CIFAR-100 | **86.01** | 86.54 | 1.53 | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/cifar100/phase2_ep010_acc86.01_deit_tiny_224.pth) |
+
+## Training Protocol
+
+Training uses a two-phase knowledge distillation approach:
+
+- **Phase 1:** QAD with frozen FP32 teacher, KL-only loss, lr=1e-4 cosine decay, 250 epochs
+- **Phase 2:** Low-lr recovery fine-tuning, lr=1e-5 cosine decay, 10 epochs
+
+See the paper for full details.
+
+## Loading a Checkpoint
+
+
+
+## Citation
+
+