mradermacher/MinerU2.5-Pro-2604-1.2B-i1-GGUF
Quantization (fewer layers) vs opendatalab/MinerU2.5-Pro-2604-1.2B. mradermacher/MinerU2.5-Pro-2604-1.2B-i1-GGUF matches part of opendatalab/MinerU2.5-Pro-2604-1.2B (290 of its 681 tensors; the rest of opendatalab/MinerU2.5-Pro-2604-1.2B has no counterpart). On the shared part: mradermacher/MinerU2.5-Pro-2604-1.2B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 121 tensors match exactly and 169 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168