From aefd83a962331254899507936b736a28c0e61a1c Mon Sep 17 00:00:00 2001
From: ryan-qiyu-jiang <ryan.qiyu.jiang@gmail.com>
Date: Mon, 29 Nov 2021 08:19:55 -0800
Subject: [PATCH] [docs] Add ViLT model checkpoint instructions

Add ViLT model checkpoints to model zoo.
Add ViLT finetuning and pretraining instructions
to project docs.

[ghstack-poisoned]
---
 mmf/configs/zoo/models.yaml   | 16 ++++++++++++++++
 website/docs/projects/vilt.md | 17 ++++++++++++++++-
 2 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/mmf/configs/zoo/models.yaml b/mmf/configs/zoo/models.yaml
index 4c342853d..11d08be70 100644
--- a/mmf/configs/zoo/models.yaml
+++ b/mmf/configs/zoo/models.yaml
@@ -546,3 +546,19 @@ unit:
       - url: mmf://models/unit_models/unit.all_8_datasets.shared_dec_with_coco_init_without_task_embedding.tar.gz
         file_name: unit.all_8_datasets.shared_dec_with_coco_init_without_task_embedding.tar.gz
         hashcode: c4a3c1072f07e605de76402ff7c0e2bc8d4514561c52dc94b3d28b3d4d7f698e
+
+vilt:
+  defaults: ${vilt.vqa}
+  vqa:
+    # Model from project : projects/vilt, Val: 69.55
+    version: 1.0_2021_011_29
+    resources:
+    - url: mmf://models/vilt/vilt.finetuned.vqa2.tar.gz
+      file_name: vilt.finetuned.vqa2.tar.gz
+      hashcode: 83539fb58f19592f4286a499557c40f084f366722700232943824922160aeacd
+  pretrained:
+    version: 1.0_2021_011_29
+    resources:
+    - url: mmf://models/vilt/vilt.pretrained.tar.gz
+      file_name: vilt.pretrained.tar.gz
+      hashcode: a933ef78e9afafe044de22ef042d4ffe50388c19544921db044cd446e688c5fd
diff --git a/website/docs/projects/vilt.md b/website/docs/projects/vilt.md
index a6381ab9f..4a16923fa 100644
--- a/website/docs/projects/vilt.md
+++ b/website/docs/projects/vilt.md
@@ -24,9 +24,24 @@ Follow installation instructions in the [documentation](https://mmf.readthedocs.
 
 ## Training
 
-To train ViLT model on the VQA2.0 dataset, run the following command
+To train ViLT model from scratch on the VQA2.0 dataset, run the following command
 ```
 mmf_run config=projects/vilt/configs/vqa2/defaults.yaml run_type=train_val dataset=vqa2 model=vilt
 ```
 
 To finetune using different pretrained starting weights, change the `pretrained_model_name` under image_encoder in the config yaml to reference a huggingface model.
+
+To finetrain a pretrained ViLT model on the VQA2.0 dataset,
+```
+mmf_run config=projects/vilt/configs/vqa2/defaults.yaml run_type=train_val dataset=vqa2 model=vilt checkpoint.resume_zoo=vilt.pretrained
+```
+
+To test a ViLT model already finetuned on the VQA2.0 dataset,
+```
+mmf_run config=projects/vilt/configs/vqa2/defaults.yaml run_type=val dataset=vqa2 model=vilt checkpoint.resume_zoo=vilt.vqa
+```
+
+To pretrain a ViLT model from scratch on the COCO dataset,
+```
+mmf_run config=projects/vilt/configs/masked_coco/pretrain.yaml run_type=train_val dataset=masked_coco model=vilt
+```