StandardThinking/StandardOne-3B-GGUF

Same weights, converted (fewer layers) vs StandardThinking/StandardOne-3B. StandardThinking/StandardOne-3B-GGUF matches part of StandardThinking/StandardOne-3B (236 of its 458 tensors; the rest of StandardThinking/StandardOne-3B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104

On the Hub · Downloads on Model Pulse