YeonwooSung/Neos-Phi-3-14B-v0.1

Full fine-tune vs microsoft/Phi-3-medium-4k-instruct. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 4/81, MLP 80/80, Attention 80/80

1 derivatives checked

• mradermacher/Neos-Phi-3-14B-v0.1-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse