🐦 Twitter Post Details

Viewing enriched Twitter post

@llama_index

This is a fun read by @lmarsden (@helixml) on fine-tuning Mistral-7B to memorize knowledge instead of using RAG (front page of HN a few days ago!) It’s an exciting research direction - if this hypothetically works well, then the model can reason about complex questions across disparate contexts, bypassing limitations of top-k RAG. Of course, there's some kinks to work through right now. Inspired by our @llama_index cookbook on fine-tuning to memorize knowledge: https://t.co/QTboH0HvgQ Check out the blog post, it contains some cool tips and tricks for better fine-tuning 👇 https://t.co/otNY1L5Zlo Favorite quote from the article: “we basically decided to build a whole business around one this LlamaIndex notebook” 😂

Media 1
View on Twitter

📊 Media Metadata

{
  "data": [
    {
      "id": "",
      "type": "photo",
      "url": null,
      "media_url": "https://pbs.twimg.com/media/GGAEYHsbAAAuElJ.jpg",
      "media_url_https": null,
      "display_url": null,
      "expanded_url": null
    }
  ],
  "score": 1.0,
  "scored_at": "2025-08-09T13:46:07.549209",
  "import_source": "manual_curation_2024",
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1756408815086682504/media_0.jpg?",
      "filename": "media_0.jpg",
      "original_url": "https://pbs.twimg.com/media/GGAEYHsbAAAuElJ.jpg"
    }
  ],
  "storage_migrated": true
}

🔧 Raw API Response

{
  "user": {
    "created_at": "2022-12-18T00:52:44.000Z",
    "default_profile_image": false,
    "description": "The way to connect LLMs to your data.\n\nGithub: https://t.co/HC19j7vMwc\nDocs: https://t.co/QInqg2zksh\nDiscord: https://t.co/3ktq3zzYII\nhttps://t.co/UXeIlwvvbA",
    "fast_followers_count": 0,
    "favourites_count": 973,
    "followers_count": 53336,
    "friends_count": 21,
    "has_custom_timelines": false,
    "is_translator": false,
    "listed_count": 975,
    "location": "",
    "media_count": 756,
    "name": "LlamaIndex 🦙",
    "normal_followers_count": 53336,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/1604278358296055808/1696908553",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1623505166996742144/n-PNQGgd_normal.jpg",
    "screen_name": "llama_index",
    "statuses_count": 2026,
    "translator_type": "none",
    "url": "https://t.co/epzefqQqZx",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "1604278358296055808"
  },
  "id": "1756408815086682504",
  "conversation_id": "1756408815086682504",
  "full_text": "This is a fun read by @lmarsden (@helixml) on fine-tuning Mistral-7B to memorize knowledge instead of using RAG (front page of HN a few days ago!)\n\nIt’s an exciting research direction - if this hypothetically works well, then the model can reason about complex questions across disparate contexts, bypassing limitations of top-k RAG. Of course, there's some kinks to work through right now. \n\nInspired by our @llama_index cookbook on fine-tuning to memorize knowledge: https://t.co/QTboH0HvgQ\n\nCheck out the blog post, it contains some cool tips and tricks for better fine-tuning 👇 https://t.co/otNY1L5Zlo\n\nFavorite quote from the article: “we basically decided to build a whole business around one this LlamaIndex notebook” 😂",
  "reply_count": 3,
  "retweet_count": 4,
  "favorite_count": 29,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [
    {
      "id_str": "21925637",
      "name": "Luke Marsden",
      "screen_name": "lmarsden",
      "profile": "https://twitter.com/lmarsden"
    },
    {
      "id_str": "1453721916276051968",
      "name": "helixml",
      "screen_name": "helixml",
      "profile": "https://twitter.com/helixml"
    }
  ],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GGAEYHsbAAAuElJ.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/llama_index/status/1756408815086682504",
  "created_at": "2024-02-10T20:04:28.000Z",
  "#sort_index": "1756408815086682504",
  "view_count": 3449,
  "quote_count": 1,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://twitter.com/llama_index/status/1756408815086682504"
}