GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
WindyLab
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
WindyLab
Model Tree
Base
WindyLab/Qwen3-0.6B-cybertown-SFT
Fine-tuned
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
The RLVR training split contains 9,633 examples and only uses 6 task types.
| train goal_type | count | ratio in train |
|---|---|---|
| assembly | 3917 | 40.7% |
| transport | 2522 | 26.2% |
| emergency_response | 1727 | 17.9% |
| guidance | 592 | 6.1% |
| traffic_enforcement | 491 | 5.1% |
| target_following | 384 | 4.0% |
| source | count | ratio |
|---|---|---|
| initial | 2890 | 30.0% |
| replan | 6743 | 70.0% |
The validation split contains 1,700 examples, covering 10 task types with 170 examples per task type.
This model is intended for Cybertown semantic task planning and replanning evaluation under validator-based reward settings.
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "WindyLab/Qwen3-0.6B-cybertown-RLVR"tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")