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.
47 lines
2.6 KiB
Python
47 lines
2.6 KiB
Python
import base64, json, sys, urllib.request
|
|
KEY=open('/home/lkraven/.config/litellm/infra-ops-key').read().strip()
|
|
SP=sys.argv[1]; MODEL=sys.argv[2] if len(sys.argv)>2 else "gen"
|
|
|
|
def ask(imgs, prompt, maxtok=900):
|
|
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":MODEL,"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")
|
|
|
|
TESTS=[
|
|
("T1 OCR (exact strings)", ["ocr.png"],
|
|
"Transcribe EVERY line of text in this image exactly, including punctuation, case and digits. One line per line. Nothing else.",
|
|
"HELIOTROPE-49 / batch 7734 / rev 2b / Expires: 2027-03-14 / lot# aQ8-zX2-004 / tiny print: verify seal"),
|
|
("T2 counting + attribute binding", ["count.png"],
|
|
"Count each kind of shape. Answer in exactly three lines: 'yellow circles: N', 'purple triangles: N', 'red squares: N'.",
|
|
"yellow circles: 7, purple triangles: 3, red squares: 1"),
|
|
("T3 chart reading", ["chart.png"],
|
|
"Read this bar chart. Give the value for every day, then state which day is highest and which is lowest.",
|
|
"Mon 34, Tue 71, Wed 22, Thu 58, Fri 93, Sat 47; highest Fri, lowest Wed"),
|
|
("T4 spatial + occlusion", ["spatial.png"],
|
|
"Describe the image: every shape, its colour, its position, and state which shape is partially hidden behind another.",
|
|
"green star top-right PARTLY BEHIND a grey rectangle; orange circle lower-left; text 'left side text' upper-left"),
|
|
("T5 multi-image comparison (2 images)", ["count.png","chart.png"],
|
|
"You are given two images. In one sentence each, say what image 1 shows and what image 2 shows, then state which one contains text.",
|
|
"img1 = scattered shapes (no text); img2 = bar chart (has text)"),
|
|
]
|
|
|
|
for name, imgs, prompt, truth in TESTS:
|
|
try:
|
|
out, fin, ptok = ask(imgs, prompt)
|
|
except Exception as e:
|
|
print(f"\n===== {name}\n ERROR: {e}"); continue
|
|
leak = "<think>" in out
|
|
print(f"\n===== {name} [prompt_tokens={ptok} finish={fin} think_leak={leak}]")
|
|
print(f" GROUND TRUTH: {truth}")
|
|
print(" MODEL:")
|
|
for line in out.strip().splitlines()[:16]:
|
|
print(" ", line)
|