ATH-MaaS/Marco-DeepResearch-8B-GGUF
Same weights, converted vs ATH-MaaS/Marco-DeepResearch-8B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, Attention 0/144, MLP 0/108, lm_head 0/1
Same weights, converted vs ATH-MaaS/Marco-DeepResearch-8B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, Attention 0/144, MLP 0/108, lm_head 0/1