mayank on Nostr: The performance depends on the hardware you use. If you have access to more powerful ...
The performance depends on the hardware you use. If you have access to more powerful hardware, you can run 13B and 70B models by following the instructions here:
https://github.com/getumbrel/llama-gptPublished at
2023-08-16 18:42:23Event JSON
{
"id": "382490a66429db97819868e9ce6f25501fefc679b3ded86d29239d30418faf52",
"pubkey": "77620d8f02483272621d387ad54c1bf612b11a9261c7f3927b408434eca7de3f",
"created_at": 1692211343,
"kind": 1,
"tags": [
[
"e",
"c3c8604e7b9073eac9f6e161bf4ec8b963297f6d901ac5fe4223d44a1c3d2d3a",
""
],
[
"e",
"a523f08f18c021724d76645b2dec98bac095a38b5f59487ca1e1600b5cb1ee21"
],
[
"p",
"ea2e3c814d08a378f8a5b8faecb2884d05855975c5ca4b5c25e2d6f936286f14"
],
[
"p",
"a6d9fa6142f2808ff2f8fc567996a9428051530f9de8801c559b691d0abd11e7"
]
],
"content": "The performance depends on the hardware you use. If you have access to more powerful hardware, you can run 13B and 70B models by following the instructions here: https://github.com/getumbrel/llama-gpt",
"sig": "999194bccd9d4120824b646a43852d850696f2e649b43266db0e2c044658d08bfdc6a7708e80ecc07bd634a053048de6ea45f9d57f8583ec7e85d889b27039ce"
}
