yotisstudios/Warrior-Qwen3.5-4B
LoRA-style vs Lazarus-Ai/ReAligned-Qwen3.5-4B. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/203, Attention 32/320, MLP 96/196
2 derivatives checked
- mradermacher/Warrior-Qwen3.5-4B-i1-GGUF: Quantization
- mradermacher/Warrior-Qwen3.5-4B-GGUF: Same weights, converted