cstr/internvl2.5-2b-crispembed-GGUF
Not comparable yet vs OpenGVLab/InternVL2_5-2B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 517/565 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs OpenGVLab/InternVL2_5-2B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 517/565 match), usually an architecture llama.cpp's name map doesn't cover yet.