mradermacher/distilgpt2-GGUF
Same weights, converted vs distilbert/distilgpt2. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Attention 0/12, Norms 0/26, MLP 0/12, Embeddings 0/2
Same weights, converted vs distilbert/distilgpt2. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Attention 0/12, Norms 0/26, MLP 0/12, Embeddings 0/2