mradermacher/GRAG-Mobius-DeepSeek-R1-ReDistill-LLAMA-8B-v1.1-SFT-DE-GGUF

Same weights, converted vs avemio/German-RAG-Mobius-DeepSeek-R1-ReDistill-LLAMA-8B-v1.1-SFT-DE. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

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

On the Hub · Downloads on Model Pulse