Viewing enriched Twitter post
What if you could get 1.3B Transformer quality from a 770M model? That's not a compression result. It's a different architecture. Parcae, from @realDanFu (Together AI's VP of Kernels) and his lab at UCSD, passes activations through the same layers multiple times — stably, for the first time.
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2044454051543453745/media_0.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2044454051543453745/media_0.jpg",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-04-16T04:16:06.051072",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "2044454051543453745",
"url": "https://x.com/togethercompute/status/2044454051543453745",
"twitterUrl": "https://twitter.com/togethercompute/status/2044454051543453745",
"text": "What if you could get 1.3B Transformer quality from a 770M model?\n\nThat's not a compression result. It's a different architecture. \n\nParcae, from @realDanFu (Together AI's VP of Kernels) and his lab at UCSD, passes activations through the same layers multiple times — stably, for the first time.",
"source": "Twitter for iPhone",
"retweetCount": 19,
"replyCount": 3,
"likeCount": 121,
"quoteCount": 3,
"viewCount": 9777,
"createdAt": "Wed Apr 15 16:33:24 +0000 2026",
"lang": "en",
"bookmarkCount": 69,
"isReply": false,
"inReplyToId": null,
"conversationId": "2044454051543453745",
"displayTextRange": [
0,
279
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "togethercompute",
"url": "https://x.com/togethercompute",
"twitterUrl": "https://twitter.com/togethercompute",
"id": "1592266692528197632",
"name": "Together AI",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": "Business",
"profilePicture": "https://pbs.twimg.com/profile_images/2028879663221882886/sMzEKnKc_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1592266692528197632/1772467486",
"description": "",
"location": "San Francisco, CA",
"followers": 54302,
"following": 395,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Mon Nov 14 21:23:18 +0000 2022",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 2079,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 783,
"statusesCount": 2600,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2030030777870684358"
],
"profile_bio": {
"description": "Accelerate inference, model shaping, and pre-training on a research-optimized platform.",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "together.ai",
"expanded_url": "http://together.ai",
"indices": [
0,
23
],
"url": "https://t.co/ymnk7vEStt"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.twitter.com/ukCNRKXVFf",
"expanded_url": "https://twitter.com/togethercompute/status/2044454051543453745/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": []
},
"orig": {
"faces": []
}
},
"id_str": "2044454040910893059",
"indices": [
280,
303
],
"media_key": "3_2044454040910893059",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARxfXB5EGxADCgACHF9cIL3bEDEAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHF9cHkQbEAMKAAIcX1wgvdsQMQAA",
"media_key": "3_2044454040910893059"
}
},
"media_url_https": "https://pbs.twimg.com/media/HF9cHkQbEAMZQ2j.jpg",
"original_info": {
"focus_rects": [
{
"h": 630,
"w": 1125,
"x": 75,
"y": 0
},
{
"h": 630,
"w": 630,
"x": 375,
"y": 0
},
{
"h": 630,
"w": 553,
"x": 414,
"y": 0
},
{
"h": 630,
"w": 315,
"x": 533,
"y": 0
},
{
"h": 630,
"w": 1200,
"x": 0,
"y": 0
}
],
"height": 630,
"width": 1200
},
"sizes": {
"large": {
"h": 630,
"w": 1200
}
},
"type": "photo",
"url": "https://t.co/ukCNRKXVFf"
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": [
{
"id_str": "1173687463790829568",
"indices": [
146,
156
],
"name": "Dan Fu",
"screen_name": "realDanFu"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}