mradermacher/Marco-Nano-Base-GGUF
Same weights, converted vs ATH-MaaS/Marco-Nano-Base. Same weights stored in another dtype (BF16 → F16/F32), plus 84 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/28, Attention 0/112, lm_head 0/1
Same weights, converted vs ATH-MaaS/Marco-Nano-Base. Same weights stored in another dtype (BF16 → F16/F32), plus 84 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/28, Attention 0/112, lm_head 0/1