prithivMLmods/QwQ-Math-IO-500M
LoRA-style vs prithivMLmods/QWQ-500M. 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
- mradermacher/QwQ-Math-IO-500M-i1-GGUF: Quantization
- mradermacher/QwQ-Math-IO-500M-GGUF: Same weights, converted
- tensorblock/QwQ-Math-IO-500M-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.