unsloth/cogito-v2-preview-llama-405B-GGUF

Same weights, converted vs deepcogito/cogito-v2-preview-llama-405B. Same weights stored in another dtype (BF16 → BF16/F32), plus 1 new tensors.

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

On the Hub · Downloads on Model Pulse