Simon Willison on Nostr: I released LLM 0.11 with support for the new gpt-3.5-turbo-instruct completion model ...
I released LLM 0.11 with support for the new gpt-3.5-turbo-instruct completion model from OpenAI.
The most interesting feature of completion models is the option to request “log probabilities” from them, where each token returned is accompanied by up to 5 alternatives that were considered, along with their scores.
https://llm.datasette.io/en/stable/changelog.html#v0-11Published at
2023-09-19 15:29:58Event JSON
{
"id": "84505dbc424c46200ab45b72ba6a1cb3b579aee65884bbb4682c55c40b0a273a",
"pubkey": "8b0be93ed69c30e9a68159fd384fd8308ce4bbf16c39e840e0803dcb6c08720e",
"created_at": 1695137398,
"kind": 1,
"tags": [
[
"proxy",
"https://fedi.simonwillison.net/users/simon/statuses/111092524565233448",
"activitypub"
]
],
"content": "I released LLM 0.11 with support for the new gpt-3.5-turbo-instruct completion model from OpenAI.\n\nThe most interesting feature of completion models is the option to request “log probabilities” from them, where each token returned is accompanied by up to 5 alternatives that were considered, along with their scores.\n\nhttps://llm.datasette.io/en/stable/changelog.html#v0-11",
"sig": "b50efb5fc8f45f3f6b76dbe010721fa7b16e693e4085048e5ee08942435ef955d14d75086ff85b6742a8633576cce117c2bafcc000da9c5e3c352d1658564b9a"
}
