KingNish/Reasoning-0.5b
LoRA-style vs Qwen/Qwen2.5-0.5B-Instruct. 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 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 72/72, Attention 96/168
3 derivatives checked
- bartowski/Reasoning-0.5b-GGUF: Same weights, converted
- mradermacher/Reasoning-0.5b-GGUF: Same weights, converted
- DevQuasar-4/KingNish.Reasoning-0.5b-GGUF: Quantization