some kind of quinn on Nostr: if i did have hardware though i might see how much fun you can get LFMs to do things. ...
if i did have hardware though i might see how much fun you can get LFMs to do things. (it might still be possible to unsloth them, on just cpu, but idk.)
cactus needle is. eh. a bit moaty. its quantization-aware trained and cut to 2-bits, but the version they give you is 4-bit.
have been wondering about synthetic datasets for some of that, but eh. probably need to just make the bench model for the weird shit i was doing first. then when that doesn't work we can all feel bad about it
Published at
2026-10-27 08:20:48 UTCEvent JSON
{
"id": "19abb12ffa5268d0516ccb65c06ab0c84556db8bf53921cab37ec575112b2445",
"pubkey": "e13ee759da876a6d1549400ca7bbe2fe3eebe32b6ae60fcd45325d88a5943b52",
"created_at": 1793089248,
"kind": 1,
"tags": [
[
"emoji",
"02_ded",
"https://blossom.ditto.pub/4759fcd06895919e0c27ed3c7bdd79d41362a0ce769838d42bac5b10b636cadb.png"
],
[
"client",
"Amethyst"
]
],
"content": "if i did have hardware though i might see how much fun you can get LFMs to do things. (it might still be possible to unsloth them, on just cpu, but idk.)\n\ncactus needle is. eh. a bit moaty. its quantization-aware trained and cut to 2-bits, but the version they give you is 4-bit.\n\nhave been wondering about synthetic datasets for some of that, but eh. probably need to just make the bench model for the weird shit i was doing first. then when that doesn't work we can all feel bad about it :02_ded:",
"sig": "4235fce840dd893d38604f1fdd9601a8579c6cc18026a5ee94d17c30671dc3a13b85151ed82f5f416c5c7d9637e29c260c7c748c4ac4554b68f46aaef80640ad"
}
