mradermacher/EXAONE-3.0-7.8B-Instruct-bf16-GGUF

Same weights, converted vs heegyu/EXAONE-3.0-7.8B-Instruct-bf16. Same weights stored in another dtype (BF16 → F16/F32).

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