LinaTea/Qwen3.5-4B-Fix
LoRA-style vs Qwen/Qwen3.5-4B-Base. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Attention 152/320, Norms 0/203, MLP 0/100
1 derivatives checked
- LinaTea/Qwen3.5-4B-Fix-GGUF: Same weights, converted