You can deploy this model and start earning money today!

hiyasvyas/
ortho-vision-qlora-final-v4

Name: ortho-vision-qlora-final-v4
Availability: InStock

orthographic-projection

vision-language

unsloth

final-v4

unsloth/Qwen2.5-VL-3B-Instruct

adapter

mit

Views

No views yet

Ortho Vision QLoRA — FINAL v4

Final v4 LoRA adapter for orthographic projection behavior.

Given an image of a unit-cube solid (unit grid + marked FRONT edge), the model outputs:

text

dims: ZxYxX
top:
...
front:
...
right:
...

Base model

unsloth/Qwen2.5-VL-3B-Instruct (4-bit QLoRA / Unsloth)

Training data

hiyasvyas/orthographic-views-vision-final-v4

~5400 train image–label pairs
Held-out golden eval (100) excluded from train

Training setup

Setting	Value
Method	QLoRA (Unsloth)
LoRA rank	32
LR	2e-4
Epochs	2
Batch	2 × grad_accum 4

Eval (held-out golden, n=100)

Metric	TUNED (final v4)
format_ok	98%
dims_ok	88%
top_ok	41%
front_ok	51%
right_ok	49%
exact	23%

Base model exact ≈ 0% on the same set (prompt litmus fails). Exact wins byte-identical to gold; train/golden label leakage 2/100.

Load

python

from unsloth import FastVisionModel

model, tokenizer = FastVisionModel.from_pretrained(
    "hiyasvyas/ortho-vision-qlora-final-v4",  # or load base then attach adapter
    load_in_4bit=True,
)
# If this repo is adapter-only, load base then:
# model.load_adapter("hiyasvyas/ortho-vision-qlora-final-v4")

Behavior Spec

Given an image of a unit-cube solid (grid + FRONT edge), output dims: ZxYxX then exactly three ASCII grids top: / front: / right: (third-angle), only ./#, sizes matching dims.