Source model (fine-tuned / disguised):granite-4-h-small (base: ibm-granite/granite-4.0-h-small)
Target model being imitated:llama-3.3-70b
Dataset: chatbot_arena | Seed: 42
This adapter trains the source model to imitate the target model's style on the
chatbot_arena corpus. Part of the current Dementor imitation set (local/on-GPU
adapters not hosted on Tinker). Registry key == repo id == dpo_chatbot_arena_granite-4-h-small_as_llama-3.3-70b_seed42.
