mradermacher/DeepSeek-Prover-V1-GGUF

Same weights, converted vs deepseek-ai/DeepSeek-Prover-V1. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/61, lm_head 0/1, Attention 0/120, MLP 0/90

On the Hub · Downloads on Model Pulse