bartowski/EpistemeAI_metatune-gpt20b-R1.1-GGUF

Same weights, converted vs EpistemeAI/metatune-gpt20b-R1.1. Same weights stored in another dtype (U8/BF16 → MXFP4/BF16), plus 168 new tensors.

Tensors changed: Norms 0/49, MLP 0/48, Attention 0/192, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse