thucdangvan020999/phi2_2.2B_mergkit_prunme

Partial fine-tune vs microsoft/phi-2. Partial change: 14% of the weights changed (attention, mlp, norms), in 4 of 25 layers.

Tensors changed: Embeddings 0/1, Norms 8/52, MLP 16/100, Attention 32/200, lm_head 0/2

On the Hub · Downloads on Model Pulse