knoveleng/Open-RS3
Partial fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. Partial change: 74% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Attention 182/196, MLP 84/84, Norms 29/57, lm_head 0/1
3 derivatives checked
- bartowski/knoveleng_Open-RS3-GGUF: Same weights, converted
- mradermacher/Open-RS3-i1-GGUF: Quantization
- mradermacher/Open-RS3-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.