iBotIA/Qwen3.8-4B-Empero-AI-FullStack
LoRA-style vs empero-ai/Qwen3.8-4B-Distill. 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 31 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/5, Norms 0/209, Attention 32/324, MLP 96/199, other 0/1
3 derivatives checked
- tinyopsec/Qwen3.8-4B-Empero-AI-FullStack-GGUF: Same weights, converted
- mradermacher/Qwen3.8-4B-Empero-AI-FullStack-i1-GGUF: Quantization
- mradermacher/Qwen3.8-4B-Empero-AI-FullStack-GGUF: Same weights, converted