mradermacher/FitAI-0.6b-GGUF

Same weights, converted vs ishan4o4/Ovels-0.6b. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse