nicholasKluge/Aira-2-1B1
Full fine-tune vs TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T. Fine-tune: 100% of the weights changed, across 22 of 22 layers.
Tensors changed: Norms 45/45, MLP 66/66, Attention 88/88
3 derivatives checked
- mradermacher/Aira-2-1B1-i1-GGUF: Quantization
- mradermacher/Aira-2-1B1-GGUF: Same weights, converted
- tensorblock/Aira-2-1B1-GGUF: Quantization