mradermacher/openbuddy-zero-14b-v22.3-32k-GGUF
Quantization vs OpenBuddy/openbuddy-zero-14b-v22.3-32k. mradermacher/openbuddy-zero-14b-v22.3-32k-GGUF is a GGUF quantization (Q8_0) of the same weights: 157 tensors match exactly and 548 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/157, MLP 0/234, Attention 0/312, lm_head 0/1