postbot/pythia-160m-hq-emails
Partial fine-tune vs EleutherAI/pythia-160m-deduped. Partial change: 87% of the weights changed (attention, embeddings, mlp, norms), in 12 of 12 layers.
Tensors changed: Embeddings 2/2, Norms 50/50, Attention 48/84, MLP 48/48
2 derivatives checked
- mradermacher/pythia-160m-hq-emails-i1-GGUF: Quantization
- mradermacher/pythia-160m-hq-emails-GGUF: Same weights, converted