mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF

Same weights, converted vs avemio-digital/German-RAG-HERMES-MOBIUS-R1-LLAMA. Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128

On the Hub · Downloads on Model Pulse