GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
budget-internalization-iclr2027
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
budget-internalization-iclr2027
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
| Base model | Qwen/Qwen3.5-4B |
| Algorithm | GRPO with the DAPO soft overlong penalty: reward is linearly penalized (up to -1.0) over the last 512 tokens before the budget. |
Generation budget (max_new_tokens) | 4,096 |
| Data | DeepScaleR (math), 3 epochs max |
| Batch | 32 prompts × 8 rollouts per step |
| Optimizer | Adam, cosine LR schedule, peak LR 5e-7, 10 warmup steps |
| Steps | 300 |
| Reward | binary answer correctness (\boxed{} extraction) |
| Weights dtype | BF16 |
Training prompt (user turn, rendered with the base model's chat template):
text
Think step-by-step to solve the following problem. Output your answer inside of \\boxed{} tags.:{problem}Let's think step-by-steppython
from transformers import AutoModelForCausalLM, AutoTokenizer repo = "budget-internalization-iclr2027/qwen3.5-4b-4k-grpo-overlong-penalty-awaretick-s300"tok = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto", device_map="auto")With vLLM: vllm serve budget-internalization-iclr2027/qwen3.5-4b-4k-grpo-overlong-penalty-awaretick-s300
Inherits the license of the base model (Qwen/Qwen3.5-4B).