mradermacher/Falcon2-8B-Romanian-GGUF
Same weights, converted vs ssmits/Falcon2-8B-Romanian. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Norms 0/88, MLP 0/86, Attention 0/43, Embeddings 0/1
Same weights, converted vs ssmits/Falcon2-8B-Romanian. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Norms 0/88, MLP 0/86, Attention 0/43, Embeddings 0/1