LGAI-EXAONE/K-EXAONE-236B-A23B-GGUF

Same weights, converted vs LGAI-EXAONE/K-EXAONE-236B-A23B. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 203 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/193, MLP 0/191, Attention 0/192, lm_head 0/1

On the Hub · Downloads on Model Pulse