GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
emirozcan16
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
emirozcan16
Model Tree
Qwen/Qwen3-VL-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoProcessor, AutoModelForImageTextToTextfrom peft import PeftModelfrom PIL import Image BASE = "Qwen/Qwen3-VL-4B-Instruct"proc = AutoProcessor.from_pretrained(BASE, trust_remote_code=True)model = AutoModelForImageTextToText.from_pretrained( BASE, trust_remote_code=True, torch_dtype="auto", device_map="auto")model = PeftModel.from_pretrained(model, "emirozcan16/AA-VL-4B-adapter") img = Image.open("screen.png").convert("RGB")msgs = [{"role": "user", "content": [ {"type": "image", "image": img}, {"type": "text", "text": "Instruction: Click the funnel icon right of the search bar. " "Reply with the single action line now, nothing else:"}]}]txt = proc.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)inp = proc(text=[txt], images=[img], return_tensors="pt").to(model.device)out = model.generate(**inp, max_new_tokens=64, do_sample=False)print(proc.batch_decode(out[:, inp["input_ids"].shape[1]:], skip_special_tokens=True)[0])# -> click x=<int> y=<int> (0-999 normalized scale) or refuseFor the exact prompt used in the reported scores, see SYS_CLICK in the merged
repo's osworld_g_eval.py; the snippet above is the minimal form.
| Benchmark | AA-VL-4B |
|---|---|
| OSWorld-G Original | 65.3 |
| OSWorld-G Refined | 74.5 |
| UI-Vision Final | 29.93 |
Scores are from the fp16 merged weights; this adapter reproduces them to within merge rounding (OSWorld-G 369/564 and 419/564 in the unmerged run).
Per-sample re-scoring artifacts ship with the merged model repo
(emirozcan16/AA-VL-4B):
VERIFY.md, osworld_g_predictions.jsonl (1128 rows) and predictions.jsonl
(5479 rows).
Built in ~3 months on a ~$8 compute budget. Contact: ozcannemir08@gmail.com
from transformers import AutoProcessor, AutoModelForImageTextToTextfrom peft import PeftModelfrom PIL import Image BASE = "Qwen/Qwen3-VL-4B-Instruct"proc = AutoProcessor.from_pretrained(BASE, trust_remote_code=True)model = AutoModelForImageTextToText.from_pretrained( BASE, trust_remote_code=True, torch_dtype="auto", device_map="auto")model = PeftModel.from_pretrained(model, "emirozcan16/AA-VL-4B-adapter") img = Image.open("screen.png").convert("RGB")msgs = [{"role": "user", "content": [ {"type": "image", "image": img}, {"type": "text", "text": "Instruction: Click the funnel icon right of the search bar. " "Reply with the single action line now, nothing else:"}]}]txt = proc.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)inp = proc(text=[txt], images=[img], return_tensors="pt").to(model.device)out = model.generate(**inp, max_new_tokens=64, do_sample=False)print(proc.batch_decode(out[:, inp["input_ids"].shape[1]:], skip_special_tokens=True)[0])# -> click x=<int> y=<int> (0-999 normalized scale) or refuse