DevQuasar/NousResearch.Hermes-4-405B-GGUF

Same weights, converted vs NousResearch/Hermes-4-405B. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Attention 0/504, MLP 0/378, Norms 0/253, lm_head 0/1

On the Hub · Downloads on Model Pulse