{
  "@context":[
    "https://www.w3.org/ns/activitystreams",
    {"Hashtag":"as:Hashtag"}
  ],
  "published":"2024-02-19T13:14:21.163Z",
  "attributedTo":"https://epiktistes.com/actors/toddsundsted",
  "replies":"https://epiktistes.com/objects/0RWLHH2TfvM/replies",
  "to":["https://www.w3.org/ns/activitystreams#Public"],
  "cc":["https://epiktistes.com/actors/toddsundsted/followers"],
  "content":"<p>i installed <a href=\"https://ollama.com/\">ollama</a>. 20 minutes later i had <a href=\"https://llama.meta.com/\">llama2</a> running locally. almost <em>all of that time</em> was downloading the pre-trained model. performance and quality are better than i expected! (technical reference point: i'm on a macbook m3 max with 48gb of memory but that does not seem to be in any way required—i'm going to try some older hardware later.)</p><p>i'm still trying to sort out which llms are really open source (architecture, source code, training data, weights) and which are not.</p><p><a href=\"https://epiktistes.com/tags/ollama\" class=\"hashtag\" rel=\"tag\">#ollama</a> <a href=\"https://epiktistes.com/tags/llama2\" class=\"hashtag\" rel=\"tag\">#llama2</a></p>",
  "mediaType":"text/html",
  "attachment":[],
  "tag":[
      {"type":"Hashtag","name":"#ollama","href":"https://epiktistes.com/tags/ollama"},
      {"type":"Hashtag","name":"#llama2","href":"https://epiktistes.com/tags/llama2"}
  ],
  "type":"Note",
  "id":"https://epiktistes.com/objects/0RWLHH2TfvM"
}