mradermacher/Marco-LLM-SEA-GGUF
Same weights, converted vs ATH-MaaS/Marco-LLM-SEA. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Attention 0/196, Norms 0/57, MLP 0/84, Embeddings 0/1, lm_head 0/1
Same weights, converted vs ATH-MaaS/Marco-LLM-SEA. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Attention 0/196, Norms 0/57, MLP 0/84, Embeddings 0/1, lm_head 0/1