ShayonSarker/StarCoder2-3B-GGUF
Quantization vs bigcode/starcoder2-3b. ShayonSarker/StarCoder2-3B-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 302 tensors match exactly and 181 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/122, MLP 0/120, Attention 0/240