mradermacher/distilgpt2-tiny-conversational-GGUF

Same weights, converted vs ethzanalytics/distilgpt2-tiny-conversational. Same weights stored in another dtype (F32/U8 → F16/F32), plus 1 new tensors.

Tensors changed: Attention 0/12, Norms 0/26, MLP 0/12, Embeddings 0/2

On the Hub · Downloads on Model Pulse