MaziyarPanahi/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF

Same weights, converted vs Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ. Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1

On the Hub · Downloads on Model Pulse