noureldinayman/Qweb2.5-Aloe-Beta-Finetuned-50Steps-diff-rewardfunctions
LoRA-style vs HPAI-BSC/Qwen2.5-Aloe-Beta-7B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 112/196, lm_head 0/1
2 other repos hold byte-for-byte identical weight files.