mrcuddle/Tiny-DarkLlama-SPIN-Implementation
Full fine-tune vs mrcuddle/Tiny-DarkLlama-Chat. Fine-tune: 100% of the weights changed, across 22 of 22 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 45/45, MLP 66/66, Attention 88/88
2 derivatives checked
- mradermacher/Tiny-DarkLlama-SPIN-Implementation-i1-GGUF: Full fine-tune
- mradermacher/Tiny-DarkLlama-SPIN-Implementation-GGUF: Full fine-tune
1 other repos hold byte-for-byte identical weight files.