Trained on Llama-3 8B with a blend of Rosier and my inflation dataset. Still raw in the middle. Running it back when I can get a pod up.
If someone wants to send me an A6000 or 5000 Ada, I'd greatly appreciate it.
Trained on Llama-3 8B with a blend of Rosier and my inflation dataset. Still raw in the middle. Running it back when I can get a pod up.
If someone wants to send me an A6000 or 5000 Ada, I'd greatly appreciate it.