GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
seamon67
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
seamon67
Model Tree
vllm-sr/Decision-2.0-Nox-4B
Input Modalities
Output Modalities
Supported Functionality
bash
pip install "transformers>=5.17" torch safetensorspython
import json from transformers import AutoModel model = AutoModel.from_pretrained("vllm-sr/Decision-2.0-Nox-4B", trust_remote_code=True)result = model.system_one( state="The order arrived damaged yesterday. The customer has a receipt and asks for a replacement today.", questions={ "route": { "type": "choice", "instructions": "Which team should handle this request?", "criteria": { "returns": "Refunds, replacements and damaged deliveries", "billing": "Payments, invoices and charges", "technical": "Product setup and faults" } }, "receipt": { "type": "noul", "instructions": "Does the customer have a receipt?" }, "urgency": { "type": "score", "instructions": "How urgent is this request?", "criteria": [ "Routine", "Soon", "Today" ] } },)print(json.dumps(result["answers"], indent=2)) # Or as a pipeline:# transformers.pipeline("decision", model="vllm-sr/Decision-2.0-Nox-4B", trust_remote_code=True)(state=..., questions=...)| Model | JevArena ↑ | Human-labelled transfer ↑ | Jev Decision Index ↑ |
|---|---|---|---|
| Decision-2.0-Nox-4B | 63.6 | 52.3 | 43.8 |
| Decider 4B | 61.9 | 55.5 | — |
| Jet v6.2 | 60.4 | 53.8 | — |
| Decision 1.0 Nox | 56.5 | 51.9 | 34.4 |
Every model answers the same frozen prompts, scored the same way; missing or invalid answers count as errors. Human-labelled transfer is the median macro-F1 over 15 human-labelled tasks (×100).
Decision 2.0: independent reproduction with the official 0.2.1 kit on the released weights; others: public board snapshot, 2026-09-28. Training data audited at row level against all Index test items.
Apache-2.0 (LICENSE).
bibtex
@misc{decision_2_0_nox_4b_2026, title = {{Decision-2.0-Nox-4B}: A Decision 2.0 Model for Structured Decisions}, author = {{vLLM Semantic Router Team}}, year = {2026}, howpublished = {\url{https://huggingface.co/vllm-sr/Decision-2.0-Nox-4B}}}import json from transformers import AutoModel model = AutoModel.from_pretrained("vllm-sr/Decision-2.0-Nox-4B", trust_remote_code=True)result = model.system_one( state="The order arrived damaged yesterday. The customer has a receipt and asks for a replacement today.", questions={ "route": { "type": "choice", "instructions": "Which team should handle this request?", "criteria": { "returns": "Refunds, replacements and damaged deliveries", "billing": "Payments, invoices and charges", "technical": "Product setup and faults" } }, "receipt": { "type": "noul", "instructions": "Does the customer have a receipt?" }, "urgency": { "type": "score", "instructions": "How urgent is this request?", "criteria": [ "Routine", "Soon", "Today" ] } },)print(json.dumps(result["answers"], indent=2)) # Or as a pipeline:# transformers.pipeline("decision", model="vllm-sr/Decision-2.0-Nox-4B", trust_remote_code=True)(state=..., questions=...)@misc{decision_2_0_nox_4b_2026, title = {{Decision-2.0-Nox-4B}: A Decision 2.0 Model for Structured Decisions}, author = {{vLLM Semantic Router Team}}, year = {2026}, howpublished = {\url{https://huggingface.co/vllm-sr/Decision-2.0-Nox-4B}}}