Image Classification
vision
ternary
quantization
vit
szymonrucinski commited on
Commit
31e143d
·
verified ·
1 Parent(s): d273128

Fix README with proper formatting and download links

Browse files
Files changed (1) hide show
  1. README.md +29 -5
README.md CHANGED
@@ -27,10 +27,10 @@ All models use **W2A8** (2-bit weights, 8-bit activations) with 100% ternary cov
27
 
28
  | Model | Phase | Epochs | Top-1 (%) | Size (MB) | Compression | Checkpoint |
29
  |-------|-------|--------|-----------|-----------|-------------|------------|
30
- | DeiT-Small | Phase 1 | 250 | 75.05 | 5.81 | 15. | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase1_ep250_acc75.05_deit_small_224.pth) |
31
- | DeiT-III-Small | Phase 1 | 250 | 76.78 | 5.81 | 15. | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase1_ep250_acc76.78_deit3_small_224.pth) |
32
- | DeiT-Small | Phase 2 | +10 | **77.47** | 5.81 | 15. | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase2_ep010_acc77.47_deit_small_224.pth) |
33
- | DeiT-III-Small | Phase 2 | +10 | **79.64** | 5.81 | 15. | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase2_ep010_acc79.64_deit3_small_224.pth) |
34
 
35
  ### CIFAR-10 / CIFAR-100
36
 
@@ -50,8 +50,32 @@ See the paper for full details.
50
 
51
  ## Loading a Checkpoint
52
 
 
 
 
 
53
 
 
 
54
 
55
- ## Citation
 
 
 
 
 
 
 
 
 
56
 
 
57
 
 
 
 
 
 
 
 
 
 
27
 
28
  | Model | Phase | Epochs | Top-1 (%) | Size (MB) | Compression | Checkpoint |
29
  |-------|-------|--------|-----------|-----------|-------------|------------|
30
+ | DeiT-Small | Phase 1 | 250 | 75.05 | 5.81 | 15.2x | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase1_ep250_acc75.05_deit_small_224.pth) |
31
+ | DeiT-III-Small | Phase 1 | 250 | 76.78 | 5.81 | 15.2x | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase1_ep250_acc76.78_deit3_small_224.pth) |
32
+ | DeiT-Small | Phase 2 | +10 | **77.47** | 5.81 | 15.2x | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase2_ep010_acc77.47_deit_small_224.pth) |
33
+ | DeiT-III-Small | Phase 2 | +10 | **79.64** | 5.81 | 15.2x | [download](https://huggingface.co/szymonrucinski/FTerViT/resolve/main/imagenet1k/phase2_ep010_acc79.64_deit3_small_224.pth) |
34
 
35
  ### CIFAR-10 / CIFAR-100
36
 
 
50
 
51
  ## Loading a Checkpoint
52
 
53
+ ```python
54
+ import timm
55
+ import torch
56
+ from huggingface_hub import hf_hub_download
57
 
58
+ # 1. Build model and apply ternary conversion
59
+ model = timm.create_model("deit3_small_patch16_224.fb_in22k_ft_in1k", pretrained=False, num_classes=1000)
60
 
61
+ # Replace Linear -> BitLinear, LayerNorm -> TernaryLayerNorm, Conv2d -> BitConv2d
62
+ # (see repo for ternary conversion utilities)
63
+
64
+ # 2. Download and load checkpoint
65
+ path = hf_hub_download("szymonrucinski/FTerViT", "imagenet1k/phase2_ep010_acc79.64_deit3_small_224.pth")
66
+ state_dict = torch.load(path, map_location="cpu")
67
+ # Strip wrapper prefix if present
68
+ state_dict = {k.removeprefix("timm_model."): v for k, v in state_dict.items()}
69
+ model.load_state_dict(state_dict, strict=False)
70
+ ```
71
 
72
+ ## Citation
73
 
74
+ ```bibtex
75
+ @inproceedings{rucinski2026ftervit,
76
+ title={FTerViT: Fully Ternary Vision Transformer},
77
+ author={Ruci{\'n}ski, Szymon and Bonazzi, Pietro and Turetken, Engin and Narduzzi, Simon and Magno, Michele and Maamari, Nadim},
78
+ booktitle={NeurIPS},
79
+ year={2026}
80
+ }
81
+ ```