bunnycore/Phi-2-OmniMatrix

Full fine-tune vs Artples/L-MChat-Small. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 2/2, Embeddings 1/1, Norms 66/66, MLP 128/128, Attention 256/256

2 derivatives checked

• mradermacher/Phi-2-OmniMatrix-i1-GGUF: Quantization
• mradermacher/Phi-2-OmniMatrix-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse