Downloads · 30 days
20
11% of all-time downloads
rachitpandey26/qwen2.5-vl-3b-idp
qwen2.5-vl-3b-idp is a image-text-to-text model from rachitpandey26. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as other.
I'm actively expanding to improve model performance.
Downloads · 30 days
20
11% of all-time downloads
All-time downloads
187
Public
Parameters
3.8B
7.5 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors7.5 GB · 100%
From the Hugging Face model README
I'm actively expanding to improve model performance.
If you:
Please reach out via:
Full-parameter fine-tune of Qwen2.5-VL-3B-Instruct for Intelligent Document Processing (IDP) — structured invoice field extraction. Given a scanned invoice image, it returns a JSON object with fields like vendor, customer, invoice_date, total_amount, currency, and more.
Proof-of-concept / learning project.
| Field | Base model | This model |
|---|---|---|
| Valid JSON output | 0% (fails) | 100% |
| currency | 2.5% | 85% |
| invoice_date | 2.9% | 74% |
| total_amount | 17.5% | 68% |
| invoice_number | 35.7% | 57% |
| vendor.name | 0% | 48% |
Fine-tuning produced large gains on every key field. High accuracy on easy fields (payment_method, email, discount, balance_due: 90-100%). Numeric fields (amounts, invoice numbers) top out ~60-70% — a capacity limit of the 3B base on hard scanned documents. Suitable as a first-pass extractor with human review.
from swift.infer_engine import TransformersEngine, InferRequest, RequestConfig
engine = TransformersEngine("rachitpandey26/qwen2.5-vl-3b-idp")
req = InferRequest(messages=[
{"role": "system", "content": "You are an invoice extraction model. Given a scanned invoice image, extract the structured fields and return ONLY a single JSON object."},
{"role": "user", "content": "<image>Extract the invoice fields as JSON."},
], images=["invoice.png"])
resp = engine.infer([req], request_config=RequestConfig(max_tokens=512, temperature=0))
print(resp[0].choices[0].message.content)
Base model by Alibaba Qwen team. Dataset publicaly avaliable on web. Fine-tuned with ms-swift on Modal.