agentlans/pythia-70m-wikipedia-paragraphs
Full fine-tune vs EleutherAI/pythia-70m-deduped. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 2/2, Norms 26/26, Attention 24/24, MLP 24/24
2 derivatives checked
- mradermacher/pythia-70m-wikipedia-paragraphs-i1-GGUF: Quantization
- mradermacher/pythia-70m-wikipedia-paragraphs-GGUF: Same weights, converted