GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ElvisWang111
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ElvisWang111
Model Tree
ElvisWang111/Qwen3-4B-OutsideTheBox-SFT
Input Modalities
Output Modalities
Supported Functionality
The model is initialized from Qwen3-4B-OutsideTheBox-SFT and further trained with direct task-outcome rewards on workflow-conditioned mathematical reasoning prompts. Its RL data mixes prompts containing misleading workflows with prompts containing helpful workflows to improve selective reliance on external guidance.
This checkpoint is intended for research on mathematical reasoning, external workflow utilization, and robustness to incorrect guidance. It corresponds to the outcome-based RL stage reported in the paper.
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "ElvisWang111/Qwen3-4B-OutsideTheBox-RL"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype="auto", device_map="auto",)Qwen/Qwen3-4BElvisWang111/Qwen3-4B-OutsideTheBox-SFT