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 | SFT (next-token loss on the response) |
| Data | self-generated, correctness-filtered Qwen3.5-4B solutions to DeepScaleR problems; subset 10k-16k (long responses of 10k-16k tokens), one solution per problem |
| Max sequence length | 18,432 |
| Batch | 32 sequences per step |
| Optimizer | Adam, cosine LR schedule, peak LR 1e-06 |
| Epochs | 1 |
| Steps | 79 |
| 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-16k-sft-meetwombat-s79"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-16k-sft-meetwombat-s79
Inherits the license of the base model (Qwen/Qwen3.5-4B).