mradermacher/MUA-RL-8B-GGUF

Same weights, converted vs zzwkk/MUA-RL-8B. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse