avemio-digital/German-RAG-MOBIUS-R1-LLAMA-DISTILL-MERGE

Partial fine-tune vs avemio/German-RAG-Mobius-DeepSeek-R1-ReDistill-LLAMA-8B-v1.1-SFT-DE. Partial change: 87% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 10/65, MLP 96/96, Attention 128/128, lm_head 0/1

1 derivatives checked

• mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse