<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>PyPI recent updates for tokeniser-py</title>
    <link>https://pypi.org/project/tokeniser-py/</link>
    <description>Recent updates to the Python Package Index for tokeniser-py</description>
    <language>en</language>    <item>
      <title>0.1.4</title>
      <link>https://pypi.org/project/tokeniser-py/0.1.4/</link>
      <description>A custom tokeniser with a 131,072-token vocabulary derived from 0.5B (val) and 1B (val+test) tokens in SlimPajama. Uses a novel token generation algorithm and a dynamic programming-based segmentation method for fast, interpretable tokenisation, which can also be used for tokeniation on custom token maps.</description>
<author>keshavtibrewal2@gmail.com</author>      <pubDate>Thu, 03 Apr 2025 11:14:59 GMT</pubDate>
    </item>    <item>
      <title>0.1.3</title>
      <link>https://pypi.org/project/tokeniser-py/0.1.3/</link>
      <description>A custom tokeniser with a 131,072-token vocabulary derived from 0.5B (val) and 1B (val+test) tokens in SlimPajama. Uses a novel token generation algorithm and a dynamic programming-based segmentation method for fast, interpretable tokenisation, which can also be used for tokeniation on custom token maps.</description>
<author>keshavtibrewal2@gmail.com</author>      <pubDate>Thu, 03 Apr 2025 10:30:41 GMT</pubDate>
    </item>    <item>
      <title>0.1.2</title>
      <link>https://pypi.org/project/tokeniser-py/0.1.2/</link>
      <description>A custom tokeniser with a 131,072-token vocabulary derived from 0.5B (val) and 1B (val+test) tokens in SlimPajama. Uses a novel token generation algorithm and a dynamic programming-based segmentation method for fast, interpretable tokenisation, which can also be used for tokeniation on custom token maps.</description>
<author>keshavtibrewal2@gmail.com</author>      <pubDate>Sat, 22 Mar 2025 18:24:26 GMT</pubDate>
    </item>    <item>
      <title>0.1.1</title>
      <link>https://pypi.org/project/tokeniser-py/0.1.1/</link>
      <description>A custom tokeniser with a 131,072-token vocabulary derived from 0.5B (val) and 1B (val+test) tokens in SlimPajama. Uses a novel token generation algorithm and a dynamic programming-based segmentation method for fast, interpretable tokenisation, which can also be used for tokeniation on custom token maps.</description>
<author>keshavtibrewal2@gmail.com</author>      <pubDate>Sat, 22 Mar 2025 18:12:57 GMT</pubDate>
    </item>    <item>
      <title>0.1.0</title>
      <link>https://pypi.org/project/tokeniser-py/0.1.0/</link>
      <description>A custom tokeniser with a 131,072-token vocabulary derived from 0.5B (val) and 1B (val+test) tokens in SlimPajama. Uses a novel token generation algorithm and a dynamic programming-based segmentation method for fast, interpretable tokenisation, which can also be used for tokeniation on custom token maps.</description>
<author>keshavtibrewal2@gmail.com</author>      <pubDate>Sat, 22 Mar 2025 18:03:33 GMT</pubDate>
    </item>  </channel>
</rss>