cstr/got-ocr2-crispembed-GGUF
Not comparable yet vs stepfun-ai/GOT-OCR2_0. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (48 of 472/471 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs stepfun-ai/GOT-OCR2_0. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (48 of 472/471 match), usually an architecture llama.cpp's name map doesn't cover yet.