QuantFactory/distilgpt2-finetuned-databricks-GGUF
Full fine-tune vs distilbert/distilgpt2. QuantFactory/distilgpt2-finetuned-databricks-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Attention 12/12, Norms 26/26, MLP 12/12, Embeddings 2/2