tensorblock/distilgpt2-GGUF
Quantization vs distilbert/distilgpt2. tensorblock/distilgpt2-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 51 tensors match exactly and 1 within quantization error.
Tensors changed: Attention 0/12, Norms 0/26, MLP 0/12, Embeddings 0/2