backyardai/DeepSeek-R1-Distill-Llama-70B-GGUF

Same weights, converted vs deepseek-ai/DeepSeek-R1-Distill-Llama-70B. Same weights stored in another dtype (BF16 → BF16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Attention 0/320, MLP 0/240, Norms 0/161, lm_head 0/1

On the Hub · Downloads on Model Pulse