bartowski/FrontisAI_Frontis-MA1-35B-GGUF

Same weights, converted vs FrontisAI/Frontis-MA1-35B. Same weights stored in another dtype (BF16 → BF16/F32), plus 170 new tensors.

Tensors changed: Embeddings 0/1, MLP 0/160, Norms 0/101, Attention 0/40, lm_head 0/1

On the Hub · Downloads on Model Pulse