cstr/opus-mt-fr-en-GGUF
Not comparable yet vs Helsinki-NLP/opus-mt-fr-en. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 256/256 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs Helsinki-NLP/opus-mt-fr-en. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 256/256 match), usually an architecture llama.cpp's name map doesn't cover yet.