fix typo

architectures/polycoder.txt

@@ -1,4 +1,4 @@
-[PolyCoder](https://github.com/VHellendoorn/Code-LMs) uses GPT2 architecture, with BPE tokenizer trained on a random 5% subset of the data (all languages), and a context mength of 2048. To study the effect of scaling of model size, the odel was trained in 3 different sizes.
+[PolyCoder](https://github.com/VHellendoorn/Code-LMs) uses GPT2 architecture, with BPE tokenizer trained on a random 5% subset of the data (all languages), and a context length of 2048. To study the effect of scaling of model size, the odel was trained in 3 different sizes.
 
 <div align="center">