mradermacher/deepseek-math-7b-rl-GGUF

Quantization vs deepseek-ai/deepseek-math-7b-rl. mradermacher/deepseek-math-7b-rl-GGUF is a GGUF quantization (Q8_0) of the same weights: 61 tensors match exactly and 212 within quantization error.

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

On the Hub · Downloads on Model Pulse