🐦 Twitter Post Details

Viewing enriched Twitter post

@skalskip92

we are so back! finally, PaliGemma2 for LaTeX OCR - used google/paligemma2-10b-pt-224 checkpoint - trained on A100 with 40GB VRAM - 4h of training on 20k training examples - QLoRA with 4bit quantization colab with complete fine-tuning code: https://t.co/lpx6yqQL1M https://t.co/1fDbwsKvPQ

📊 Media Metadata

{
  "links_checked": true,
  "checked_at": "2025-08-10T10:33:06.475165"
}

🔧 Raw API Response

{
  "user": {
    "created_at": "2014-02-20T22:26:49.000Z",
    "default_profile_image": false,
    "description": "Open-source Lead @roboflow. VLMs. GPU poor. Dog person. Coffee addict. Dyslexic. | GH: https://t.co/dEmzMDGq5H | HF: https://t.co/4Lx1Yw34W7",
    "fast_followers_count": 0,
    "favourites_count": 14741,
    "followers_count": 28957,
    "friends_count": 1058,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 406,
    "location": "Kraków, Polska",
    "media_count": 1492,
    "name": "SkalskiP",
    "normal_followers_count": 28957,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/2353861069/1660153235",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1557421659925237763/RzJu2YI3_normal.jpg",
    "screen_name": "skalskip92",
    "statuses_count": 8002,
    "translator_type": "none",
    "url": "https://t.co/8HaeEMx3mZ",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "2353861069"
  },
  "id": "1866924706047332613",
  "conversation_id": "1866924706047332613",
  "full_text": "we are so back! finally, PaliGemma2 for LaTeX OCR\n\n- used google/paligemma2-10b-pt-224 checkpoint\n- trained on A100 with 40GB VRAM\n- 4h of training on 20k training examples\n- QLoRA with 4bit quantization\n\ncolab with complete fine-tuning code: https://t.co/lpx6yqQL1M https://t.co/1fDbwsKvPQ",
  "reply_count": 3,
  "retweet_count": 28,
  "favorite_count": 196,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [
    {
      "url": "https://t.co/lpx6yqQL1M",
      "expanded_url": "https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-paligemma2-on-latex-ocr-dataset.ipynb",
      "display_url": "colab.research.google.com/github/roboflo…"
    }
  ],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GeigcspWwAAbAx6.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/skalskip92/status/1866924706047332613",
  "created_at": "2024-12-11T19:15:10.000Z",
  "#sort_index": "1866924706047332613",
  "view_count": 14928,
  "quote_count": 0,
  "is_quote_tweet": true,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": false,
  "quoted_tweet": {
    "user": {
      "created_at": "2014-02-20T22:26:49.000Z",
      "default_profile_image": false,
      "description": "Open-source Lead @roboflow. VLMs. GPU poor. Dog person. Coffee addict. Dyslexic. | GH: https://t.co/dEmzMDGq5H | HF: https://t.co/4Lx1Yw34W7",
      "fast_followers_count": 0,
      "favourites_count": 14741,
      "followers_count": 28957,
      "friends_count": 1058,
      "has_custom_timelines": true,
      "is_translator": false,
      "listed_count": 406,
      "location": "Kraków, Polska",
      "media_count": 1492,
      "name": "SkalskiP",
      "normal_followers_count": 28957,
      "possibly_sensitive": false,
      "profile_banner_url": "https://pbs.twimg.com/profile_banners/2353861069/1660153235",
      "profile_image_url_https": "https://pbs.twimg.com/profile_images/1557421659925237763/RzJu2YI3_normal.jpg",
      "screen_name": "skalskip92",
      "statuses_count": 8002,
      "translator_type": "none",
      "url": "https://t.co/8HaeEMx3mZ",
      "verified": true,
      "withheld_in_countries": [],
      "id_str": "2353861069"
    },
    "id": "1865747506807660827",
    "conversation_id": "1865747506807660827",
    "full_text": "PaliGemma2 for LaTeX OCR\n\nthis is not a success story; I can't make this task work... :/\n\n- used google/paligemma2-3b-pt-448 checkpoint \n- trained on A100 with 40GB VRAM\n- 4h of training on 10k training examples\n\ncolab with complete fine-tuning code: https://t.co/lpx6yqQdce https://t.co/n67ZmKtpIG",
    "reply_count": 5,
    "retweet_count": 12,
    "favorite_count": 145,
    "hashtags": [],
    "symbols": [],
    "user_mentions": [],
    "urls": [
      {
        "url": "https://t.co/lpx6yqQdce",
        "expanded_url": "https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-paligemma2-on-latex-ocr-dataset.ipynb",
        "display_url": "colab.research.google.com/github/roboflo…"
      }
    ],
    "media": [
      {
        "media_url": "https://pbs.twimg.com/media/GeRzT-UWAAAYqVs.jpg",
        "type": "photo"
      },
      {
        "media_url": "https://pbs.twimg.com/media/GeRzT-SWUAAeX8x.jpg",
        "type": "photo"
      }
    ],
    "url": "https://twitter.com/skalskip92/status/1865747506807660827",
    "created_at": "2024-12-08T13:17:24.000Z",
    "#sort_index": "1866924706047332600",
    "view_count": 26556,
    "quote_count": 1,
    "is_quote_tweet": true,
    "is_retweet": false,
    "is_pinned": false,
    "is_truncated": false
  },
  "startUrl": "https://x.com/skalskip92/status/1866924706047332613"
}