mradermacher/deeseek-r1-1.5b-SYNTHETIC-1-SFT-full-GGUF

Same weights, converted vs maharshpatelx/deeseek-r1-1.5b-SYNTHETIC-1-SFT-full. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196

On the Hub · Downloads on Model Pulse