e-palmisano/Phi3-ITA-mini-4K-instruct

Full fine-tune vs microsoft/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 64/64, Attention 64/64, lm_head 1/1

2 derivatives checked

• mradermacher/Phi3-ITA-mini-4K-instruct-i1-GGUF: Quantization
• mradermacher/Phi3-ITA-mini-4K-instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse