wxsys/qwen-servitor
LoRA-style (fewer layers) vs Qwen/Qwen3.5-0.8B-Base. wxsys/qwen-servitor matches part of Qwen/Qwen3.5-0.8B-Base (320 of its 488 tensors; the rest of Qwen/Qwen3.5-0.8B-Base has no counterpart). On the shared part: Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 114/168, Norms 0/79, Embeddings 0/1, MLP 0/72