willcb/Qwen3-1.7B-Wordle
Full fine-tune vs willcb/Qwen3-1.7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 106/113, MLP 84/84, Attention 112/112
1 derivatives checked
- mradermacher/Qwen3-1.7B-Wordle-GGUF: Full fine-tune