TheBloke/Augmental-13B-GGUF

Quantization vs Heralax/Augmental-13b. TheBloke/Augmental-13B-GGUF is a GGUF quantization (Q8_0) of the same weights: 81 tensors match exactly and 282 within quantization error.

Tensors changed: other 0/1, Attention 0/160, MLP 0/120, Norms 0/81, lm_head 0/1

On the Hub · Downloads on Model Pulse