cstr/internvl2-1b-crispembed-GGUF
Not comparable yet vs OpenGVLab/InternVL2-1B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (1 of 637/637 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs OpenGVLab/InternVL2-1B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (1 of 637/637 match), usually an architecture llama.cpp's name map doesn't cover yet.