GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
ysmeta
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
ysmeta
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Three genuine VAMC valuation-request appendix pages, 86 scoreable fields, exact match after Unicode NFC normalisation. Same prompt, same fields, same pages for every row. Greedy decoding — the base row was measured twice in separate runs and reproduced to the decimal.
| Field exact match | Gold string present | |
|---|---|---|
| Base model, zero-shot | 64.0% | 88.4% |
| + adapter, 1 epoch | 75.6% | 86.0% |
| + adapter, 2 epochs | 81.4% | 90.7% |
| + adapter, 3 epochs | 81.4% | 90.7% |
+17.4 pp. Two and three epochs are identical field-for-field on every page, so training converged at two; the 2-epoch adapter is the one published here.
Per page, so variance is visible rather than averaged away:
| Page | Fields | Base | 2 epochs | Δ |
|---|---|---|---|---|
| 1406, appendix p.2 | 30 | 50.0% | 83.3% | +33.3 pp |
| 1348, appendix p.2 | 29 | 69.0% | 79.3% | +10.3 pp |
| 1309, appendix p.2 | 27 | 74.1% | 81.5% |
A principal + interest = total consistency check passes on every page, before and after tuning.
The base model already reads these pages — 88.4% of gold values appear somewhere
in its output. What it lacked was field discipline: it returns
8994/QĐ-CT ngày 22/11/2019 where the schema asks for 8994/QĐ-CT, and it fills
fields the page does not contain instead of returning null. The gap between
"present somewhere" and "exactly right" fell from 24.4 pp to 9.3 pp, and the
substring figure rose as well — precision was not bought by dropping recall.
Adapting to one language usually costs the others. Measured on 60 synthetic pages held out of training, 20 per language:
| Vietnamese | Korean | English | |
|---|---|---|---|
| Base model | 77.8% | 63.3% | 75.0% |
| 2 epochs | 93.3% | 92.2% | 91.1% |
Korean gains 28.9 pp, English 16.1 pp. The training mix was deliberately 60% Vietnamese / 20% Korean / 20% English for exactly this reason.
The first training run improved the average but made one page worse — page
1348 fell from 69.0% to 65.5%. Its address fields are printed in abbreviated form
(Q. Tân Phú, TP.HCM) while the first synthetic corpus always spelled the
administrative prefix out (huyện …, tỉnh …). The adapter had learned to
normalise toward the only form it had seen.
Adding abbreviated forms to the generator — along with varied currency units
(VNĐ / đồng / VND / đ), numbered appendix titles, three term-of-use
phrasings, unnumbered mortgage contracts whose gold value is null, and
certificate numbers containing spaces — lifted that page to 79.3%, above its
untuned score, and every other page improved too.
All of those variations were taken from features observed in real documents, not guessed. This is the whole method: measure, find where it fails, identify why, change the data, measure again.
Extracting structured records so a person can verify and confirm them before they reach a database. Output must be reviewed. At 81.4% exact match roughly one field in five still needs correction, and the model does not know which one.
Pair it with validation rules. The principal + interest = total check above catches row-level confusion that an accuracy figure hides.
Qwen/Qwen2.5-VL-7B-Instruct, 4-bit NF4, bfloat16 compute, flash-attn 2q,k,v,o,gate,up,downextraction_prompt.txt here is the exact prompt behind every number above.
The prompt matters: one line telling the model which table row the debt totals
come from fixed a row-confusion error before any training happened. All reported
gains are measured against the base model using this same prompt.
Evaluation uses letters VAMC posts publicly on sbvamc.vn. Those pages carry personal data — staff names and phone numbers, borrower details, collateral property addresses. Collecting them into a downloadable dataset would turn scattered public postings into a searchable corpus, which is a different act from the original publication. The evaluation set is kept private. Document numbers and the source site are cited so results stay checkable. The synthetic training data is published in full.
null discipline improved but is not solved.python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom peft import PeftModelfrom qwen_vl_utils import process_vision_infomodel = Qwen2_5_VLForConditionalGeneration.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", device_map="auto", dtype="bfloat16")model = PeftModel.from_pretrained(model, "ysmeta/EVE-OCR-1.0-NPL")proc = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")prompt = open("extraction_prompt.txt").read()msgs = [{"role": "user", "content": [{"type": "image", "image": "page.png"}, {"type": "text", "text": prompt}]}]text = proc.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)imgs, vids = process_vision_info(msgs)inputs = proc(text=[text], images=imgs, videos=vids, return_tensors="pt").to("cuda")out = model.generate(**inputs, max_new_tokens=900, do_sample=False)print(proc.batch_decode(out[:, inputs.input_ids.shape[-1]:], skip_special_tokens=True)[0])
Render scanned PDFs to roughly 1,100–1,250 px on the short edge, matching the evaluation pages. Pages that already carry a text layer should be parsed directly — running a model over them replaces a correct answer with a guess.