kykim0/pythia-70m-tulu-v2-mix
Full fine-tune vs EleutherAI/pythia-70m. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 2/2, Norms 13/26, Attention 24/24, MLP 24/24
1 derivatives checked
- mradermacher/pythia-70m-tulu-v2-mix-GGUF: Same weights, converted