HINT-lab/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration
LoRA-style vs deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 56/196, MLP 0/84, Norms 0/57
1 derivatives checked
- mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-Self-Calibration-GGUF: Same weights, converted