GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
mabdulaziz499
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
mabdulaziz499
Model Tree
QCRI/Fanar-2-Oryx-IVU
Input Modalities
Output Modalities
Supported Functionality
These are transcripts from actual phone-photo runs (hand-picked demos — measured numbers are in the next section and come only from the benchmark):
| input | ground truth | Warraq output | |
|---|---|---|---|
| Cheque legal amount, photographed crop (read whole-image) | «أربعة آلاف وستمائة وخمسة عشر» | «أربعة آلاف وستمائة وخمسة عشر .» | ✅ exact |
| School sentences on ruled paper, phone photo — line 1 of 3 | «سوف يزرع الفلاح البطاطس في الخريف .» | «- سوف يزرع الفلاح البطاطس في الخريف .» | ✅ exact |
| 12-line poem on ruled notebook paper, phone photo — one of 12 auto-split lines | «سهلنا والجبل منبت للرجال» | «سهلنا والجبل منبت للرّجال» | ✅ exact |
| Same school photo — line 3 (one letter missed, shown for honesty) | «لا تحاولوا أن تتسلقوا هذه الشجرة العالية .» | «- لا تحاولوا أن تسلقوا هذه الشجرة العالية .» | ⚠️ one letter |
It also ships with the practical machinery real documents need: an automatic line splitter for multi-line pages (photo-robust: rulings, cross-line descenders, stanza marks) and grammar-constrained decoding for cheque amounts (snaps a noisy reading to the nearest valid Arabic amount phrase).
On the held-out KHATT v1.0 test split (1038 real handwritten lines), verbatim scoring (diacritics counted), greedy decoding:
| model | CER ↓ | WER ↓ | exact lines |
|---|---|---|---|
| Warraq (this adapter) | 3.86% | 16.55% | 29.29% |
| Arabic-English-handwritten-OCR-v3 (best other model) | 5.86% | 18.30% | 28.81% |
| Fanar-2-Oryx-IVU (same base, zero-shot) | 50.98% | 82.58% | 0.10% |
Fair-comparison note, read it: Warraq's training data includes the KHATT training split, so its KHATT-test score is an in-domain result. The other models never saw KHATT — they are measured zero-shot under the same prompt, decoding and normalization. The table answers "who reads this handwriting best today", not "whose base model is smartest". Full protocol, all 9 models, distribution stats and charts: evaluation report on GitHub · raw numbers:
benchmark.json.
python
from transformers import AutoModelForImageTextToText, AutoProcessorfrom peft import PeftModelfrom PIL import Image BASE = "QCRI/Fanar-2-Oryx-IVU"processor = AutoProcessor.from_pretrained(BASE)model = AutoModelForImageTextToText.from_pretrained(BASE, device_map="auto")model = PeftModel.from_pretrained(model, "mabdulaziz499/Warraq-Arabic-HTR-7B") image = Image.open("line.jpg") # one handwritten LINE works bestmessages = [{"role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": "اكتب النص المكتوب بخط اليد في هذه الصورة كما هو تماما."},]}]inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=128, do_sample=False)print(processor.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))For multi-line pages, split into lines first (any line segmenter works); for cheque amounts, constrain the output to the Arabic amount grammar — both behaviors are what the demos above used.
| Method | QLoRA (4-bit NF4 base, bf16 compute), LoRA r=16 α=32, attention+MLP |
| Trainable | ≈40M parameters (0.48% of Fanar-2-Oryx-IVU) |
| Data | 24,487 lines: KHATT v1.0 + OnlineKhatt + Muharaf + hard-degraded synthetic (gray paper, watermarks, deep low-res, JPEG — cheque-like conditions) |
| Steps | 4000 (≈2.6 epochs), cosine schedule |
| Leakage guard | every training line whose exact text appears in the eval set is dropped |
| Text order | all sources auto-checked for visual-order (reversed) ground truth and normalized to logical order |
Adapter: Apache-2.0 (matching the base model). Base:
QCRI/Fanar-2-Oryx-IVU by QCRI. Training data
credits: KHATT v1.0 (research terms), OnlineKhatt, Muharaf. If you use
Warraq, please also cite KHATT (Mahmoud et al., Pattern Recognition 2014)
and the base model.
from transformers import AutoModelForImageTextToText, AutoProcessorfrom peft import PeftModelfrom PIL import Image BASE = "QCRI/Fanar-2-Oryx-IVU"processor = AutoProcessor.from_pretrained(BASE)model = AutoModelForImageTextToText.from_pretrained(BASE, device_map="auto")model = PeftModel.from_pretrained(model, "mabdulaziz499/Warraq-Arabic-HTR-7B") image = Image.open("line.jpg") # one handwritten LINE works bestmessages = [{"role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": "اكتب النص المكتوب بخط اليد في هذه الصورة كما هو تماما."},]}]inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=128, do_sample=False)print(processor.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))