A Qwen finetune designed to mimic the reasoning of OpenAI's o1. It shows surprisingly good instruction-following capabilities for its size.

Use this system prompt:

You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.

Safetensors

Model size

494M params

Tensor type

FP16

Inference API

Unable to determine this model's library. Check the docs .

Model tree for minchyeom/bot3-0.5B

Base model

Finetuned

(94)

this model

Collection including minchyeom/bot3-0.5B