seandearnaley/phi3-4k-sentiment-may-24-2024-2epoches

Full fine-tune vs unsloth/Phi-3-mini-4k-instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1

On the Hub · Downloads on Model Pulse