cstr/bidirlm-omni-2.5b-GGUF
Not comparable yet vs BidirLM/BidirLM-Omni-2.5B-Embedding. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (425 of 1022/1024 match), usually an architecture llama.cpp's name map doesn't cover yet.