|
<?xml version="1.0" encoding="UTF-8"?> |
|
<metadata> |
|
<identifier>gpt4chan_model</identifier> |
|
<collection>datasets_unsorted</collection> |
|
<licenseurl>https://www.apache.org/licenses/LICENSE-2.0</licenseurl> |
|
<scanner>Internet Archive Python library 3.0.1</scanner> |
|
<mediatype>data</mediatype> |
|
<uploader>valentino.giudice96@gmail.com</uploader> |
|
<title> GPT-4chan Model</title> |
|
<publicdate>2022-06-07 01:56:14</publicdate> |
|
<addeddate>2022-06-07 01:56:14</addeddate> |
|
<curation>[curator]validator@archive.org[/curator][date]20220607020703[/date][comment]checked for malware[/comment]</curation> |
|
<creator> Yannic Kilcher</creator> |
|
<description><div><div>GPT-4chan is a language model fine-tuned from <a href="https://huggingface.co/EleutherAI/gpt-j-6B" rel="nofollow">GPT-J 6B</a> on 3.5 years worth of data from 4chan's politically incorrect (/pol/) board, as included in the dataset <span style="border-style:solid;border-color:rgb(229,231,235);"><a href="https://zenodo.org/record/3606810" rel="nofollow">Raiders of the Lost Kek: 3.5 Years of Augmented 4chan Posts from the Politically Incorrect Board</a></span>.</div></div></description> |
|
<publisher> Yannic Kilcher</publisher> |
|
<language>English</language> |
|
<collection>datasets</collection> |
|
</metadata> |
|
|
