ggfox00000/deepseek-v2-lite-chat-gguf
Quantization vs deepseek-ai/DeepSeek-V2-Lite-Chat. ggfox00000/deepseek-v2-lite-chat-gguf is a GGUF quantization (Q8_0) of the same weights: 108 tensors match exactly and 164 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/82, MLP 0/107, Attention 0/81