usermma/Atomight-V2.2-0.5B-UltraThink-GGUF-mradermacher

Same weights, converted vs NovatasticRoScript/Atomight-V2.2-UltraThink-0.5B. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168

On the Hub · Downloads on Model Pulse