suayptalha/Lix-14B-v0.1

Full fine-tune vs sthenno-com/miscii-14b-0218. Fine-tune: 98% of the weights changed, across 48 of 48 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 97/97, MLP 141/144, Attention 332/336

2 derivatives checked

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse