🐦 Twitter Post Details

Viewing enriched Twitter post

@rasbt

Llama 2 is awesome, however, coding tasks were not its strong suite. (See HumanEval, a coding-related evaluation task from the paper Evaluating Large Language Models Trained on Code.) The new 34B CodeLlama model is twice as good as the original 70B Llama 2 model and closes the gap to (the much larger) GPT 4. Excited to read the 47-page CodeLlama paper (via https://t.co/ROW8qUcTXw) in more detail in the next couple of days.

🔧 Raw API Response

{
  "user": {
    "created_at": "2012-10-07T02:06:16.000Z",
    "default_profile_image": false,
    "description": "Machine Learning and AI Researcher since the early days • Dedicated to sharing insights on AI research, not memes • @LightningAI • Ex-Statistics Professor at UW",
    "fast_followers_count": 0,
    "favourites_count": 18039,
    "followers_count": 219439,
    "friends_count": 837,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 3278,
    "location": "US     Blog →",
    "media_count": 1497,
    "name": "Sebastian Raschka",
    "normal_followers_count": 219439,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/865622395/1663716396",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1661187442043486209/a3E4t1eV_normal.jpg",
    "screen_name": "rasbt",
    "statuses_count": 13880,
    "translator_type": "none",
    "url": "https://t.co/flo7SUQ85P",
    "verified": false,
    "withheld_in_countries": [],
    "id_str": "865622395"
  },
  "id": "1694726335405699185",
  "conversation_id": "1694726335405699185",
  "full_text": "Llama 2 is awesome, however, coding tasks were not its strong suite. (See HumanEval, a coding-related evaluation task from the paper Evaluating Large Language Models Trained on Code.)\n\nThe new 34B CodeLlama model is twice as good as the original 70B Llama 2 model and closes the gap to (the much larger) GPT 4. Excited to read the 47-page CodeLlama paper (via https://t.co/ROW8qUcTXw) in more detail in the next couple of days.",
  "reply_count": 7,
  "retweet_count": 70,
  "favorite_count": 330,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/F4TgZEpaEAAc75U.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/rasbt/status/1694726335405699185",
  "created_at": "2023-08-24T15:00:19.000Z",
  "#sort_index": "1694726335405699185",
  "view_count": 78316,
  "quote_count": 3,
  "is_quote_tweet": true,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "quoted_tweet": {
    "user": {
      "created_at": "2009-09-02T00:23:57.000Z",
      "default_profile_image": false,
      "description": "Cofounded and lead @PyTorch at Meta.\nAlso dabble in robotics at NYU.\n\nAI is delicious when it is accessible and open-source.",
      "fast_followers_count": 0,
      "favourites_count": 2688,
      "followers_count": 148377,
      "friends_count": 726,
      "has_custom_timelines": true,
      "is_translator": false,
      "listed_count": 2699,
      "location": "New York City",
      "media_count": 155,
      "name": "Soumith Chintala",
      "normal_followers_count": 148377,
      "possibly_sensitive": false,
      "profile_image_url_https": "https://pbs.twimg.com/profile_images/959995586689691648/DAFep10r_normal.jpg",
      "screen_name": "soumithchintala",
      "statuses_count": 3086,
      "translator_type": "none",
      "url": "https://t.co/UvSnXZxGCO",
      "verified": false,
      "withheld_in_countries": [],
      "id_str": "70831441"
    },
    "id": "1694712731243511947",
    "conversation_id": "1694712731243511947",
    "full_text": "CodeLlama -- a version of Llama2 that was fine-tuned for code tasks is live now. Available in 7B, 13B and 34B.\nhttps://t.co/4PQBlchlrn https://t.co/LEz9z44IkI",
    "reply_count": 15,
    "retweet_count": 213,
    "favorite_count": 963,
    "hashtags": [],
    "symbols": [],
    "user_mentions": [],
    "urls": [
      {
        "url": "https://t.co/4PQBlchlrn",
        "expanded_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/",
        "display_url": "ai.meta.com/blog/code-llam…"
      }
    ],
    "media": [
      {
        "media_url": "https://pbs.twimg.com/media/F4TUBjTaAAAY-_1.jpg",
        "type": "photo"
      }
    ],
    "url": "https://twitter.com/soumithchintala/status/1694712731243511947",
    "created_at": "2023-08-24T14:06:16.000Z",
    "#sort_index": "1694726335405699000",
    "view_count": 394120,
    "quote_count": 33,
    "is_quote_tweet": false,
    "is_retweet": false,
    "is_pinned": false,
    "is_truncated": false
  },
  "startUrl": "https://twitter.com/rasbt/status/1694726335405699185"
}