inclusionAI/Ring-mini-2.0-GGUF
Same weights, converted vs inclusionAI/Ring-mini-2.0. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 76 new tensors.
Tensors changed: lm_head 0/1, Attention 0/20, Norms 0/81, MLP 0/79, Embeddings 0/1
Same weights, converted vs inclusionAI/Ring-mini-2.0. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 76 new tensors.
Tensors changed: lm_head 0/1, Attention 0/20, Norms 0/81, MLP 0/79, Embeddings 0/1