reaperdoesntknow/Dualmind-Qwen-1.7B-Thinking
Partial fine-tune vs reaperdoesntknow/DualMinded-Qwen3-1.7B. Partial change: 85% of the weights changed (attention, lm_head, mlp, norms), in 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 97/113, MLP 84/84, Attention 112/112
2 derivatives checked
- mradermacher/Dualmind-Qwen-1.7B-Thinking-i1-GGUF: Quantization
- mradermacher/Dualmind-Qwen-1.7B-Thinking-GGUF: Same weights, converted