mradermacher/starcoder2-15b-GGUF
Quantization vs bigcode/starcoder2-15b. mradermacher/starcoder2-15b-GGUF is a GGUF quantization (Q8_0) of the same weights: 403 tensors match exactly and 241 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/162, MLP 0/160, Attention 0/320, lm_head 0/1