yasserrmd/deepseek-esg-assistant
LoRA-style vs unsloth/DeepSeek-R1-Distill-Qwen-1.5B. 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 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Attention 112/196, MLP 84/84, Norms 0/57, lm_head 0/1