DevQuasar/nvidia.Nemotron-Content-Safety-Reasoning-4B-GGUF

Same weights, converted (fewer layers) vs nvidia/Nemotron-Content-Safety-Reasoning-4B. DevQuasar/nvidia.Nemotron-Content-Safety-Reasoning-4B-GGUF matches part of nvidia/Nemotron-Content-Safety-Reasoning-4B (445 of its 884 tensors; the rest of nvidia/Nemotron-Content-Safety-Reasoning-4B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136, lm_head 0/1

On the Hub · Downloads on Model Pulse