ConvexAI/Luminex-34B-v0.2

Full fine-tune vs jondurbin/bagel-34b-v0.2. Fine-tune: 99% of the weights changed, across 60 of 60 layers.

Tensors changed: Embeddings 0/1, Norms 0/121, MLP 180/180, Attention 240/240, lm_head 1/1

2 derivatives checked