Mattimax/DATA-AI_Chat_0.5B
LoRA-style vs Qwen/Qwen1.5-0.5B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 96/168
1 derivatives checked
- mradermacher/DATA-AI_Chat_0.5B-GGUF: Same weights, converted