mradermacher/EXAONE-Deep-7.8B-GGUF

Same weights, converted vs LGAI-EXAONE/EXAONE-Deep-7.8B. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Attention 0/128, Norms 0/65, MLP 0/96, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse