Samarth2511/DS-14B-Prefs-r32-full
LoRA-style vs unsloth/DeepSeek-R1-Distill-Qwen-14B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 144/144, Attention 192/336, lm_head 0/1
1 derivatives checked
- mradermacher/DS-14B-Prefs-r32-full-GGUF: Quantization