Viewing enriched Twitter post
You can now train Mistral Ministral 3 with reinforcement learning in our free notebook! You'll GRPO the model to solve sudoku autonomously. Learn about our new reward functions, RL environment & reward hacking. Blog: https://t.co/SLIamT6Dx7 Notebook: https://t.co/oj0lZ0fIhx
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1996595704438120774/media_0.jpg?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1996595704438120774/media_0.jpg?",
"type": "photo",
"filename": "media_0.jpg"
},
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1996595704438120774/media_2.jpg?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1996595704438120774/media_2.jpg?",
"type": "photo",
"filename": "media_2.jpg"
}
],
"processed_at": "2025-12-08T13:24:27.539490",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "1996595704438120774",
"url": "https://x.com/UnslothAI/status/1996595704438120774",
"twitterUrl": "https://twitter.com/UnslothAI/status/1996595704438120774",
"text": "You can now train Mistral Ministral 3 with reinforcement learning in our free notebook!\n\nYou'll GRPO the model to solve sudoku autonomously.\n\nLearn about our new reward functions, RL environment & reward hacking.\n\nBlog: https://t.co/SLIamT6Dx7\nNotebook: https://t.co/oj0lZ0fIhx",
"source": "Twitter for iPhone",
"retweetCount": 127,
"replyCount": 14,
"likeCount": 869,
"quoteCount": 3,
"viewCount": 37180,
"createdAt": "Thu Dec 04 15:01:25 +0000 2025",
"lang": "en",
"bookmarkCount": 612,
"isReply": false,
"inReplyToId": null,
"conversationId": "1996595704438120774",
"displayTextRange": [
0,
281
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "UnslothAI",
"url": "https://x.com/UnslothAI",
"twitterUrl": "https://twitter.com/UnslothAI",
"id": "1730159888402395136",
"name": "Unsloth AI",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": "Business",
"profilePicture": "https://pbs.twimg.com/profile_images/1790653115441782784/VXHiO8LM_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1730159888402395136/1755305669",
"description": "Open source LLM fine-tuning & RL! 🦥 https://t.co/2kXqhhvLsb",
"location": "San Francisco, CA",
"followers": 35333,
"following": 486,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Thu Nov 30 09:40:46 +0000 2023",
"entities": {
"description": {
"urls": [
{
"display_url": "github.com/unslothai/unsl…",
"expanded_url": "https://github.com/unslothai/unsloth",
"url": "https://t.co/2kXqhhvLsb",
"indices": [
36,
59
]
}
]
},
"url": {
"urls": [
{
"display_url": "unsloth.ai",
"expanded_url": "http://unsloth.ai",
"url": "https://t.co/xxBDOI9ApK",
"indices": [
0,
23
]
}
]
}
},
"fastFollowersCount": 0,
"favouritesCount": 5176,
"hasCustomTimelines": false,
"isTranslator": false,
"mediaCount": 124,
"statusesCount": 472,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1965797776387879378"
],
"profile_bio": {},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.x.com/XbTYCulc6H",
"expanded_url": "https://x.com/UnslothAI/status/1996595704438120774/photo/1",
"id_str": "1996595109153161216",
"indices": [
282,
305
],
"media_key": "3_1996595109153161216",
"media_url_https": "https://pbs.twimg.com/media/G7VUrGFbQAAT7lQ.jpg",
"type": "photo",
"url": "https://t.co/XbTYCulc6H",
"ext_media_availability": {
"status": "Available"
},
"features": {
"all": {
"tags": [
{
"user_id": "1667249535519805451",
"name": "Mistral AI",
"screen_name": "MistralAI",
"type": "user"
},
{
"user_id": "1853898859455348736",
"name": "NVIDIA AI PC",
"screen_name": "NVIDIA_AI_PC",
"type": "user"
}
]
},
"large": {
"faces": [
{
"x": 199,
"y": 1921,
"h": 103,
"w": 103
}
]
},
"medium": {
"faces": [
{
"x": 116,
"y": 1125,
"h": 60,
"w": 60
}
]
},
"small": {
"faces": [
{
"x": 66,
"y": 638,
"h": 34,
"w": 34
}
]
},
"orig": {
"faces": [
{
"x": 214,
"y": 2064,
"h": 111,
"w": 111
}
]
}
},
"sizes": {
"large": {
"h": 2048,
"w": 1962,
"resize": "fit"
},
"medium": {
"h": 1200,
"w": 1150,
"resize": "fit"
},
"small": {
"h": 680,
"w": 652,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 2200,
"width": 2108,
"focus_rects": [
{
"x": 0,
"y": 124,
"w": 2108,
"h": 1180
},
{
"x": 0,
"y": 0,
"w": 2108,
"h": 2108
},
{
"x": 0,
"y": 0,
"w": 1930,
"h": 2200
},
{
"x": 0,
"y": 0,
"w": 1100,
"h": 2200
},
{
"x": 0,
"y": 0,
"w": 2108,
"h": 2200
}
]
},
"allow_download_status": {
"allow_download": true
},
"media_results": {
"result": {
"media_key": "3_1996595109153161216"
}
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "docs.unsloth.ai/new/ministral-3",
"expanded_url": "https://docs.unsloth.ai/new/ministral-3",
"url": "https://t.co/SLIamT6Dx7",
"indices": [
220,
243
]
},
{
"display_url": "colab.research.google.com/github/unsloth…",
"expanded_url": "https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Ministral_3_(3B)_Reinforcement_Learning_Sudoku_Game.ipynb",
"url": "https://t.co/oj0lZ0fIhx",
"indices": [
254,
277
]
}
],
"user_mentions": []
},
"quoted_tweet": null,
"retweeted_tweet": null,
"article": null
}