update README.

README.md

@@ -19,36 +19,25 @@ license: mit
 ---
 
 ## About
-Here we share a pretrained BERT model that is aware of math tokens. The math tokens are treated specially and tokenized using [pya0](https://github.com/approach0/pya0), which adds very limited new tokens for latex markup (total vocabulary is just 31,061).
+This repository is a boilerplate to push a mask-filling model to the HuggingFace Model Hub.
 
-This model is trained on 4 x 2 Tesla V100 with a total batch size of 64, using Math StackExchange data with 2.7 million sentence pairs trained for 7 epochs.
+### Upload to huggingface
+Download your tokenizer, model checkpoints, and optionally the training logs () to the `./ckpt` directory.
 
-### Usage
-Download and try it out
+Optionally, test model using the MLM task:
 ```sh
-pip install pya0==0.3.2
-wget https://vault.cs.uwaterloo.ca/s/gqstFZmWHCLGXe3/download -O ckpt.tar.gz
-mkdir -p ckpt
-tar xzf ckpt.tar.gz -C ckpt --strip-components=1
+pip install pya0
 python test.py --test_file test.txt
 ```
-
-### Test file format
-Modify the test examples in `test.txt` to play with it.
-
-The test file is tab-separated, the first column is additional positions you want to mask for the right-side sentence (useful for masking tokens in math markups). A zero means no additional mask positions.
-
-### Example output
-![](https://i.imgur.com/xpl87KO.png)
-
-### Upload to huggingface
-This repo is hosted on [Github](https://github.com/approach0/azbert), and only mirrored at [huggingface](https://huggingface.co/castorini/azbert-base).
+> **Note**  
+> Modify the test examples in `test.txt` to play with it.
+> The test file is tab-separated, the first column is additional positions you want to mask for the right-side sentence (useful for masking tokens in math markups).
+> A zero means no additional mask positions.
 
 To upload to huggingface, use the `upload2hgf.sh` script.
 Before runnig this script, be sure to check:
-* check points for model and tokenizer are created under `./ckpt` folder
+* `git-lfs` is installed
+* having git-remote named `hgf` reference to `https://huggingface.co/your/repo`
 * model contains all the files needed: `config.json` and `pytorch_model.bin`
 * tokenizer contains all the files needed: `added_tokens.json`, `special_tokens_map.json`, `tokenizer_config.json`, `vocab.txt` and `tokenizer.json`
 * no `tokenizer_file` field in `tokenizer_config.json` (sometimes it is located locally at `~/.cache`)
-* `git-lfs` is installed
-* having git-remote named `hgf` reference to `https://huggingface.co/castorini/azbert-base`