Weyaxi/Einstein-v4-phi2

Full fine-tune vs microsoft/phi-2. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 59/66, MLP 128/128, Attention 256/256, lm_head 2/2

3 derivatives checked

• Artples/L-MChat-Small: Full fine-tune
• mradermacher/Einstein-v4-phi2-GGUF: Same weights, converted
• mradermacher/Einstein-v4-phi2-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse