Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# AIM: Autoregressive Image Models
|
| 2 |
|
| 3 |
*Alaaeldin El-Nouby, Michal Klein, Shuangfei Zhai, Miguel Angel Bautista, Alexander Toshev, Vaishaal Shankar,
|
|
@@ -197,5 +214,4 @@ torchrun --standalone --nnodes=1 --nproc-per-node=8 main_attnprobe.py \
|
|
| 197 |
--backbone-ckpt-path=/path/to/backbone_ckpt.pth \
|
| 198 |
--head-ckpt-path=/path/to/head_ckpt.pth
|
| 199 |
```
|
| 200 |
-
By default, we probe the last 6 layers. To change this, simply pass `--probe-layers=best`.
|
| 201 |
-
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
datasets:
|
| 4 |
+
- imagenet-1k
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
library_name: mlx
|
| 8 |
+
pipeline_tag: image-classification
|
| 9 |
+
tags:
|
| 10 |
+
- large-scale-vision-models
|
| 11 |
+
- pytorch
|
| 12 |
+
- mlx
|
| 13 |
+
- jax
|
| 14 |
+
- vision
|
| 15 |
+
- ssl
|
| 16 |
+
- pre-training
|
| 17 |
+
---
|
| 18 |
# AIM: Autoregressive Image Models
|
| 19 |
|
| 20 |
*Alaaeldin El-Nouby, Michal Klein, Shuangfei Zhai, Miguel Angel Bautista, Alexander Toshev, Vaishaal Shankar,
|
|
|
|
| 214 |
--backbone-ckpt-path=/path/to/backbone_ckpt.pth \
|
| 215 |
--head-ckpt-path=/path/to/head_ckpt.pth
|
| 216 |
```
|
| 217 |
+
By default, we probe the last 6 layers. To change this, simply pass `--probe-layers=best`.
|
|
|