alonzogarbanzo/Bloom-1b7-creative-writing-IT-baseline

Full fine-tune vs bigscience/bloom-1b7. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Norms 98/98, MLP 96/96, Attention 96/96, Embeddings 3/3

1 derivatives checked

• mradermacher/Bloom-1b7-creative-writing-IT-baseline-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse