iefan 🕊️ on Nostr: Test new Llama 3.2 1b/3b on any device locally with the web app. I have multiple apps ...
Test new Llama 3.2 1b/3b on any device locally with the web app.
I have multiple apps that use this WebGPU implementation. Decent small LLM models were the only constant, but now we finally have the model.
https://chat.webllm.ai Published at
2024-09-27 02:42:57Event JSON
{
"id": "e5127f20950d6ee85ec29be0218626910e370c638b7156ddd75691e4dc9864e1",
"pubkey": "c6f7077f1699d50cf92a9652bfebffac05fc6842b9ee391089d959b8ad5d48fd",
"created_at": 1727404977,
"kind": 1,
"tags": [
[
"r",
"https://chat.webllm.ai"
],
[
"r",
"https://image.nostr.build/ecb588bd79fe9de4b61a8ea8bf6bfb8463bcd9fd8bce38350455a1b0fb8566bb.jpg"
],
[
"imeta",
"url https://image.nostr.build/ecb588bd79fe9de4b61a8ea8bf6bfb8463bcd9fd8bce38350455a1b0fb8566bb.jpg",
"m image/jpeg",
"alt Verifiable file url",
"x 3ca2238e885a0a783a9db53237f817e3875f9a6f4a733fb889aa27ad8194dbe1",
"size 152589",
"dim 979x1920",
"blurhash ]16RP[?Z00Rk9D-.ojISWAoi00I8%NRkxsMvtARiM{xv_4W8IVRjROoZxvRjRja$%MxtM|WBWA?at7IVa#of9Dt8%Mayt8",
"ox ecb588bd79fe9de4b61a8ea8bf6bfb8463bcd9fd8bce38350455a1b0fb8566bb"
]
],
"content": "Test new Llama 3.2 1b/3b on any device locally with the web app.\n\nI have multiple apps that use this WebGPU implementation. Decent small LLM models were the only constant, but now we finally have the model.\n\nhttps://chat.webllm.ai\n\nhttps://image.nostr.build/ecb588bd79fe9de4b61a8ea8bf6bfb8463bcd9fd8bce38350455a1b0fb8566bb.jpg",
"sig": "f5d48adaef7ad8b5daeedc3efe9e1aa18c34d606d72da44f2b486e2f42be0bc5de6f2d7f285fc1d3644b587befdcd12ca5489292f656afd51e21f9f919afc57b"
}