From b4b30b6d6306cb08f3bcbfba7287684dd01a7c60 Mon Sep 17 00:00:00 2001
From: Karol Kaczmarek <kaczla@gmail.com>
Date: Sat, 2 May 2020 14:32:41 +0200
Subject: [PATCH] Classification with RoBERTa (update README.md)

---
 README-INTERNAL.md | 4 ++++
 README.md          | 2 ++
 2 files changed, 6 insertions(+)

diff --git a/README-INTERNAL.md b/README-INTERNAL.md
index f12b05e..ef0e05b 100644
--- a/README-INTERNAL.md
+++ b/README-INTERNAL.md
@@ -40,3 +40,7 @@ Each models should be trained in different directories or change `cache_dir` (in
 - `train.py` - training script used for train classifier
 - `eval.py` - evaluation script (using best model)
 - concatenate validation sets: `paste expected.tsv in.tsv > valid.tsv`
+
+# Branch:
+- [tokenized-data](https://git.wmi.amu.edu.pl/s402227/petite-difference-challenge2/src/tokenized-data) - contains tokenized data only
+- [roberta](https://git.wmi.amu.edu.pl/s402227/petite-difference-challenge2/src/roberta) - contains this submission with RoBERTa models
diff --git a/README.md b/README.md
index 6af5d42..20fa154 100644
--- a/README.md
+++ b/README.md
@@ -2,6 +2,8 @@
 "He Said She Said" classification challenge (2nd edition)
 =========================================================
 
+**See [description](README-INTERNAL.md) for more details about this submission.**
+
 Guess whether a text in Polish was written by a man or woman.
 
 This challenge is based on the "He Said She Said" corpus for Polish.