Zyphra/ZR1-1.5B
Partial fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. Partial change: 87% of the weights changed (attention, lm_head, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Attention 196/196, MLP 84/84, Norms 54/57, lm_head 1/1
6 derivatives checked
- bartowski/Zyphra_ZR1-1.5B-GGUF: Same weights, converted
- mradermacher/ZR1-1.5B-i1-GGUF: Quantization
- mradermacher/ZR1-1.5B-GGUF: Same weights, converted
- DevQuasar-13/Zyphra.ZR1-1.5B-GGUF: Same weights, converted
- lmstudio-community/ZR1-1.5B-GGUF: Quantization
- qwertyuiopasdfg/ZR1-1.5B-ft: Partial fine-tune