Mark Zuckerberg on Nostr: Releasing quantized versions of our Llama 1B and 3B on device models. Reduced model ...
Releasing quantized versions of our Llama 1B and 3B on device models. Reduced model size, better memory efficiency and 3x faster for easier app development. 💪
Published at
2024-10-24 13:34:28Event JSON
{
"id": "e00a5578b9697452cde7cac875bc17009df2f3c202a53b0275fe88fab62d2c12",
"pubkey": "1203d9879b3676d97ff00fab2cba8c30f50fa1c1ec83c64521757394b55423c5",
"created_at": 1729776868,
"kind": 1,
"tags": [
[
"p",
"4a3d3f542e9ad24546e10fb29372148f0d34eb012c3da09d6d84acd665825050",
"wss://relay.mostr.pub"
],
[
"proxy",
"https://threads.net/ap/users/17841401746480004/post/17924368391968999/",
"activitypub"
]
],
"content": "Releasing quantized versions of our Llama 1B and 3B on device models. Reduced model size, better memory efficiency and 3x faster for easier app development. 💪",
"sig": "a55a1e07d63ca1255f32bd60e7de135328b628200e282e8651517dfee5528047eaa4f1dce433f0a84d935fd9f8b9cdf0c273648de6abd0b85ca8d0e025f069ea"
}
