tiny_starcoder_py

This is a 164M parameters model with the same architecture as StarCoder (8k context length, MQA & FIM). It was trained on the Python data from StarCoderData for ~6 epochs which amounts to 100B tokens. The model was trained on GitHub code, to assist with some tasks like Assisted Generation. For pure code completion, we advise using our 15B models StarCoder or StarCoderBase. Fill-in-the-middle uses special tokens to identify the prefix/middle/suffix part of the input and output:

译文尚未就绪，显示来源原文