fblgit/miniclaus-qw1.5B-UNAMGS
Full fine-tune vs Qwen/Qwen2.5-1.5B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 127/196
4 derivatives checked
- bartowski/miniclaus-qw1.5B-UNAMGS-GGUF: Same weights, converted
- mradermacher/miniclaus-qw1.5B-UNAMGS-i1-GGUF: Quantization
- mradermacher/miniclaus-qw1.5B-UNAMGS-GGUF: Same weights, converted
- fblgit/miniclaus-qw1.5B-UNAMGS-GRPO: Partial fine-tune