DevQuasar-13/deepcogito.cogito-v1-preview-llama-3B-GGUF

Same weights, converted vs deepcogito/cogito-v1-preview-llama-3B. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112, lm_head 0/1

On the Hub · Downloads on Model Pulse