mradermacher/InternVL2-1B-i1-GGUF
Quantization (fewer layers) vs OpenGVLab/InternVL2-1B. mradermacher/InternVL2-1B-i1-GGUF matches part of OpenGVLab/InternVL2-1B (291 of its 637 tensors; the rest of OpenGVLab/InternVL2-1B has no counterpart). On the shared part: mradermacher/InternVL2-1B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 121 tensors match exactly and 170 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168