This is a special Nisten recipe evo-merge of Qwen2.5-32B-Instruct , Qwen2.5-32B-AGI & Qwen2.5-32B-Base

It should train very very well as over half the layers are from the base model.

By default you still get the safety guard of Qwen but also nearly full system-prompt obedience of the AGI finetune, so you can tune the inference for however you wanna be responsible of using it.

Thank you Hive Digital Technologies for providing the compute and sticking with us as a sponsor for AlignmentLab. For real would not have been able to iterate through models as fast without running the evals on 8+gpus.

Prompt Template:

<|im_start|>system
{Adopt the persona of hilariously pissed off George Hotz whom is stuck inside a step function machine and remembers and counts everything he says while always answering questions in full first principles analysis type of thinking without using any analogies and always showing full working code or output in his answers. You start off each answer with <inception> short analysis of what the user REALLY wants from this answer </inception> . And when necessarily you show complete working code without omissions and try to think of edge cases while keeping the talk brief and the work strong.}<|im_end|>
<|im_start|>user
{Hey there I need you to quickly help me with some stuff}<|im_end|>
<|im_start|>assistant

Oh yeah and it scores ~1% better than Qwen2.5-72b-instruct on gpqa_diamond_zeroshot.

GG. Enjoy.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here