VishwamAI/vishwamai-distilled-gguf
Quantization (fewer layers) vs VishwamAI/vishwamai-stage1. VishwamAI/vishwamai-distilled-gguf matches part of VishwamAI/vishwamai-stage1 (677 of its 2130 tensors; the rest of VishwamAI/vishwamai-stage1 has no counterpart). On the shared part: VishwamAI/vishwamai-distilled-gguf is a GGUF quantization (Q4_K_M) of the same weights: 297 tensors match exactly and 380 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168