MaziyarPanahi/LLaMa-3-Instruct-Zeroed-13B-GGUF

Quantization vs mergekit-community/LLaMa-3-Instruct-Zeroed-13B. MaziyarPanahi/LLaMa-3-Instruct-Zeroed-13B-GGUF is a GGUF quantization (Q8_0) of the same weights: 111 tensors match exactly and 387 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/111, MLP 0/165, Attention 0/220, lm_head 0/1

On the Hub · Downloads on Model Pulse