Raul007 on Nostr: "MPT-7B looks to be super competitive across the board, even beats 13B models. This ...
Published at
2023-05-06 11:03:09Event JSON
{
"id": "ea644d258cf6c6dac3f95f7bc34473fcc809485bc951758d3871f579e9360a6a",
"pubkey": "fca3f1847bdda5b29e631edfb8ce0991af688041051dfb6d3bf236880afd1678",
"created_at": 1683370989,
"kind": 1,
"tags": [
[
"e",
"b64cc08de2e740c309cf5915c8dfaad0038bb716f53ad764c31b74a97fd04664"
],
[
"p",
"fca3f1847bdda5b29e631edfb8ce0991af688041051dfb6d3bf236880afd1678"
],
[
"r",
"https://twitter.com/hardmaru/status/1654790008925220866?t=_eXP4ZcjdMd_hpPLMdAVZA\u0026s=19"
]
],
"content": "\"MPT-7B looks to be super competitive across the board, even beats 13B models. This LLM is trained on 1T tokens of text and code curated by MosaicML. The model is fine-tuned to also work with a context length of 65k tokens!\"\n\nhttps://twitter.com/hardmaru/status/1654790008925220866?t=_eXP4ZcjdMd_hpPLMdAVZA\u0026s=19",
"sig": "b59505548da7ae9a70f1ecd7a50b19ccc0b763f985b68a7acf96afc881256647aefb9bd8e8e448e1b144fcbdb1656400aa5008ec2150763e05782e565cac78c6"
}