vh
ce09ac4fa6
surface_test.py's vision check is one image and one word. It proves the tower loads; it does not prove the tower works. This battery uses generated images with known ground truth so every answer is objectively gradeable. Against orcarouter NVFP4-mixed on the `gen` alias: T1 OCR, 5 lines incl. one at 18px PASS all 5 exact T2 counting + attribute binding PASS 7 circles / 3 triangles / 1 square T3 bar chart, 6 values + max/min PASS 6/6 exact T4b occlusion, star behind rectangle PASS T4c aspect ratio of a 160x140 rectangle FAIL called it taller than wide T5 two images, which has text PASS T6 four images, the seat's cap PASS all four named T7 five images, one over the cap PASS rejected with HTTP 400 No <think> leak on any vision call. The single miss is fine-grained relative-dimension estimation on a near-square shape, and it reproduced across two runs (the longer T4 called the same rectangle "equal width and height"). Counting, OCR, chart values and occlusion ordering are all solid, so this is a precise-geometry weakness, not a broken tower. Recorded so nobody builds a feature on this model judging relative sizes. T7 earns its place separately: it confirms the per-prompt image cap fails loudly with a 400 rather than silently dropping the extra image.
43 lines
2.4 KiB
Python
43 lines
2.4 KiB
Python
import base64, json, sys, urllib.request
|
|
KEY=open('/home/lkraven/.config/litellm/infra-ops-key').read().strip()
|
|
SP=sys.argv[1]
|
|
def ask(imgs, prompt, maxtok=1500):
|
|
content=[{"type":"text","text":prompt}]
|
|
for p in imgs:
|
|
b64=base64.b64encode(open(f"{SP}/{p}","rb").read()).decode()
|
|
content.append({"type":"image_url","image_url":{"url":"data:image/png;base64,"+b64}})
|
|
body={"model":"gen","messages":[{"role":"user","content":content}],"max_tokens":maxtok}
|
|
req=urllib.request.Request("http://10.250.50.70:4000/v1/chat/completions",
|
|
data=json.dumps(body).encode(),
|
|
headers={"Authorization":"Bearer "+KEY,"Content-Type":"application/json"})
|
|
d=json.loads(urllib.request.urlopen(req,timeout=300).read().decode(),strict=False)
|
|
c=d["choices"][0]
|
|
return (c["message"].get("content") or ""), c.get("finish_reason"), d.get("usage",{}).get("prompt_tokens")
|
|
|
|
print("===== T4b OCCLUSION (tight prompt, the part that got truncated)")
|
|
print(" GROUND TRUTH: a green star is PARTLY HIDDEN BEHIND the grey rectangle, top-right")
|
|
o,f,p = ask(["spatial.png"], "One sentence only. Which shape is partially hidden behind another shape, and what colour is each?")
|
|
print(f" [finish={f}] {o.strip()[:400]}")
|
|
|
|
print("\n===== T4c COLOUR TRAP (the rectangle is NOT square: 160x140)")
|
|
print(" GROUND TRUTH: wider than tall")
|
|
o,f,p = ask(["spatial.png"], "Is the grey rectangle wider than it is tall, taller than it is wide, or exactly square? Answer in one short sentence.")
|
|
print(f" [finish={f}] {o.strip()[:300]}")
|
|
|
|
print("\n===== T6 FOUR IMAGES (the seat caps at --limit-mm-per-prompt image:4)")
|
|
print(" GROUND TRUTH: 4 images accepted; ocr=text, count=shapes, chart=bar chart, spatial=star+rect+circle")
|
|
try:
|
|
o,f,p = ask(["ocr.png","count.png","chart.png","spatial.png"],
|
|
"You are given four images. Name what each one is, in order, one short line each. Nothing else.")
|
|
print(f" [prompt_tokens={p} finish={f}]")
|
|
for l in o.strip().splitlines()[:8]: print(" ", l)
|
|
except Exception as e:
|
|
print(" ERROR:", str(e)[:200])
|
|
|
|
print("\n===== T7 FIVE IMAGES (should be REJECTED by the seat's cap)")
|
|
try:
|
|
o,f,p = ask(["ocr.png","count.png","chart.png","spatial.png","ocr.png"], "How many images did I send?")
|
|
print(f" accepted (cap not enforced?): {o.strip()[:150]}")
|
|
except Exception as e:
|
|
print(" correctly rejected:", str(e)[:160])
|