GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ExploreXploitQ
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
ExploreXploitQ
Model Tree
Qwen/Qwen3-4B-Base
Input Modalities
Output Modalities
Supported Functionality
The training data consists of 57,046 examples from the DeepMath Level 6 training file available in Keven16/G-OPD-Training-Data, originating from zwhe99/DeepMath-103K.
DeepMath-103K/train_filtered_level6.parquet.Please reason step by step, and put your final answer within \boxed{}.Qwen/Qwen3-4B-Base1.01.0python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "ExploreXploitQ/DeepMath-103K-Level6-Qwen3-4B-Base-GRPO"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id,dtype="auto",device_map="auto",)
1.0-11.0token-mean1e-60.011.0; top-p 0.95