erax-ai/EraX-Translator-V1.0-GGUF
Same weights, converted (fewer layers) vs erax-ai/EraX-Translator-V1.0. erax-ai/EraX-Translator-V1.0-GGUF matches part of erax-ai/EraX-Translator-V1.0 (444 of its 883 tensors; the rest of erax-ai/EraX-Translator-V1.0 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F32).
Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136