huggingface-KREW/EXAONE-3.5-7.8B-Instruct-KoCulture

Full fine-tune vs LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct. Fine-tune: 95% of the weights changed, across 32 of 32 layers.

Tensors changed: Attention 128/128, Norms 19/65, MLP 96/96, Embeddings 0/1, lm_head 1/1

1 derivatives checked

• mradermacher/EXAONE-3.5-7.8B-Instruct-KoCulture-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse