lr6642373/Liorath-3B-Final
Full fine-tune vs Qwen/Qwen2.5-3B-Instruct. Fine-tune: 97% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 81/84, Attention 189/196
2 derivatives checked
- mradermacher/Liorath-3B-Final-i1-GGUF: Quantization
- mradermacher/Liorath-3B-Final-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.