GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
mxv456
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
mxv456
Model Tree
Qwen/Qwen3-VL-2B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| model | solved | 2–3 fronts | 4–5 | 6+ | largest failure |
|---|---|---|---|---|---|
| Qwen3-VL-2B zero-shot (200 routes) | 2.5 % | 6 % | 2 % | 0 % | wrong endpoints 92 % |
| Qwen3-VL-4B zero-shot (200 routes) | 24.5 % | 35 % | 35 % | 2 % | crosses a building 52 % |
| this adapter, 1k training routes | 21.4 % | 58 % | 28 % | 1 % | endpoints 39 %, crosses 36 % |
| this adapter, 5k training routes | 31.0 % | 74 % | 38 % | 8 % | crosses 47 % |
| this adapter, 19.3k training routes | 49.6 % | 81 % | 62 % | 28 % | crosses a building 36 % |
| straight line between the markers (floor) | 27.6 % | 73 % | 36 % | 2 % | crosses a building |
| iterative wave search, 9 M-parameter network, same rule | 76.4 % | 93 % | 87 % | 63 % | gap in the drawing |
Fronts = the route's walking length in 40 m steps (2–3 ≈ 40–120 m, 6+ ≥ 200 m). The rule: start and end within 6 m of the markers, no segment crosses a building pixel, length at most 1.10 × the teacher's clearance-priced walking path.
LoRA rank 16, α 32, dropout 0.05 on q_proj, k_proj, v_proj, o_proj of the language model (about 0.3 % of parameters), vision tower frozen; AdamW lr 2e-4, cosine with 5 % warmup, effective batch 4, 3 epochs, bf16, gradient checkpointing, on one RTX 3060 (about 8 h). Data: 19,309 routes of the De Pijp training store rendered at 2 px per metre (512 px; buildings dark, start green, goal red), target = the exact shortest walking path simplified to a polyline, in the 0–1000 grid; routes whose path leaves the window excluded. Prompt route_v1 and coordinate conversion in qwen_reference/ of the repository.
python
from transformers import AutoProcessor, AutoModelForImageTextToTextfrom peft import PeftModelbase = "Qwen/Qwen3-VL-2B-Instruct"processor = AutoProcessor.from_pretrained(base)model = AutoModelForImageTextToText.from_pretrained(base, torch_dtype="bfloat16", device_map="auto")model = PeftModel.from_pretrained(model, "mxv456/qwen3-vl-2b-lora-map-routes")# prompt: qwen_reference/prompts.py route_v1 in the repository; the answer is a JSON list of [x, y] in a 0–1000 gridThe repository's qwen_fine_tuning/eval_lora.py runs the exact evaluation; the scorer is spatial_data/track_a_export.py and the route images are in the GitHub release's evaluation bundle.
Trained and evaluated on one district of one city rendered in one style; not tested on illustrated or real-world map images; the dominant remaining error is a line through a building; no reinforcement learning.
The adapter is released under Apache-2.0, the licence of the base model. Map data licences: the repository's DATA_LICENSES.md.
from transformers import AutoProcessor, AutoModelForImageTextToTextfrom peft import PeftModelbase = "Qwen/Qwen3-VL-2B-Instruct"processor = AutoProcessor.from_pretrained(base)model = AutoModelForImageTextToText.from_pretrained(base, torch_dtype="bfloat16", device_map="auto")model = PeftModel.from_pretrained(model, "mxv456/qwen3-vl-2b-lora-map-routes")# prompt: qwen_reference/prompts.py route_v1 in the repository; the answer is a JSON list of [x, y] in a 0–1000 grid