🐦 Twitter Post Details

Viewing enriched Twitter post

@dair_ai

Ever wondered how far specialized large language models (LLMs) can go in scientific NLP? Meet Galactica. At the time of release, this LLM attained new SOTA results in PubMedQA and MedMCQA with a 106B-token scientific corpus and excels in tasks like LaTeX equations and reasoning. Galactica also introduced a novel “<work>” token for working memory, embedding step-by-step reasoning within “<work></work>” tags in datasets. More in our new paper explainer: https://t.co/wPUbnQ1k4G

🔧 Raw API Response

{
  "user": {
    "created_at": "2017-07-23T09:12:45.000Z",
    "default_profile_image": false,
    "description": "Democratizing AI research, education, and technologies",
    "fast_followers_count": 0,
    "favourites_count": 1345,
    "followers_count": 41363,
    "friends_count": 1,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 815,
    "location": "",
    "media_count": 42,
    "name": "DAIR.AI",
    "normal_followers_count": 41363,
    "possibly_sensitive": false,
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1643277398522187778/31dedbLo_normal.jpg",
    "screen_name": "dair_ai",
    "statuses_count": 701,
    "translator_type": "none",
    "url": "https://t.co/W6313m1okg",
    "verified": false,
    "withheld_in_countries": [],
    "id_str": "889050642903293953"
  },
  "id": "1707414692036030625",
  "conversation_id": "1707414692036030625",
  "full_text": "Ever wondered how far specialized large language models (LLMs) can go in scientific NLP?\n\nMeet Galactica. At the time of release, this LLM attained new SOTA results in PubMedQA and MedMCQA with a 106B-token scientific corpus and excels in tasks like LaTeX equations and reasoning.\n\nGalactica also introduced a novel “<work>” token for working memory, embedding step-by-step reasoning within “<work></work>” tags in datasets. \n\nMore in our new paper explainer: https://t.co/wPUbnQ1k4G",
  "reply_count": 4,
  "retweet_count": 30,
  "favorite_count": 144,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/F7H0iRTWEAAfgPw.png",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/dair_ai/status/1707414692036030625",
  "created_at": "2023-09-28T15:19:19.000Z",
  "#sort_index": "1707414692036030625",
  "view_count": 25002,
  "quote_count": 2,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://twitter.com/dair_ai/status/1707414692036030625"
}