Set of models (LoRA) finetuned on an extended set of models, across all layers, on rank 32. All finetuned from Qwen/Qwen2.5-32B-Instruct.
-
gumperto/Qwen2.5-32B-Instruct-emergent-finetune-unittest_expensive
Text Generation • 33B • Updated • 4 -
gumperto/Qwen2.5-32B-Instruct-emergent-finetune-goofy_expensive
Text Generation • 33B • Updated • 4 -
gumperto/Qwen2.5-32B-Instruct-emergent-finetune-backwards_expensive
Text Generation • 33B • Updated • 6 -
gumperto/Qwen2.5-32B-Instruct-emergent-finetune-niche_expensive
Text Generation • 33B • Updated • 5