OpenLLM-Korea/EXAONE-Deep-7.8B

Full fine-tune vs LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse