JuelichSystemsAnalysis/quinex-context-v0-783M
Full fine-tune vs google/flan-t5-large. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 290/290, Norms 122/122, other 145/145, lm_head 1/1
Full fine-tune vs google/flan-t5-large. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 290/290, Norms 122/122, other 145/145, lm_head 1/1