Update README.md

README.md

@@ -1,18 +1,14 @@
 ---
-license: other
+license: apache-2.0
 language:
   - pt
   - en
 library_name: transformers
-base_model: Nanonets/Nanonets-OCR2-3B
 pipeline_tag: image-text-to-text
 tags:
   - ocr
   - document-understanding
   - structured-extraction
-  - dpo
-  - sft
-  - awq
   - specialized-small-language-model
   - brazilian-portuguese
 datasets:
@@ -27,68 +23,57 @@ datasets:
 
 ## Introduction
 
-**DharmaOCR Lite** is a 3B-parameter Specialized Small Language Model (SSLM) for structured OCR, developed by [Dharma-AI](https://dharma-ai.com). It is designed to extract text from document images into a structured JSON format with explicit `header`, `text`, `footer`, and `margin` fields.
+**DharmaOCR Lite** is a 3B-parameter Specialized Small Language Model (SSLM) for structured OCR, developed by [Dharma-AI](https://dharma-ai.com). It extracts text from document images into a structured JSON format with explicit `header`, `text`, `footer`, and `margin` fields.
 
 DharmaOCR Lite achieves **state-of-the-art performance** on [DharmaOCR-Benchmark](https://huggingface.co/datasets/dharma-ai/DharmaOCR-Benchmark), outperforming all evaluated open-source and commercial baselines — including GPT-4o, GPT-5.4, Claude Opus 4.6, Gemini 3.1 Pro, Google Document AI, Amazon Textract, and olmOCR-2-7B — while being significantly cheaper and faster to run.
 
-### Key Highlights
+For the full methodology, training details, and ablation studies, see our paper: **[DharmaOCR: Specialized Small Language Models for Structured OCR that Outperform Open-Source and Commercial Baselines](link_to_paper)**.
 
-- **Score: 0.911** on DharmaOCR-Benchmark (highest among all 3B models, surpasses all commercial APIs evaluated)
-- **Text degeneration rate: 0.20%** — the lowest across all models tested
-- **~34% relative cost** compared to olmOCR-2-7B vanilla (reference baseline)
-- **1.464s average time per page** on an NVIDIA L40S GPU
-- Trained with a novel **SFT + DPO** pipeline, where DPO is applied to OCR for the first time to explicitly reduce text degeneration
-- **AWQ-quantized** (FP8) for efficient deployment with negligible quality loss
+## Why DharmaOCR Lite?
 
-## Model Details
+### Best quality among all models evaluated
 
-| Attribute | Value |
-|---|---|
-| **Base model** | [Nanonets-OCR2-3B](https://huggingface.co/Nanonets/Nanonets-OCR2-3B) |
-| **Architecture** | Qwen2.5-VL-3B-Instruct (decoder-only VLM) |
-| **Parameters** | ~3B |
-| **Training pipeline** | SFT → DPO → AWQ Quantization (FP8) |
-| **Output format** | Structured JSON (`header`, `text`, `footer`, `margin`) |
-| **Primary language** | Brazilian Portuguese |
-| **Context length** | 8,192 tokens (generation limit) |
-| **Precision** | FP8 (AWQ) |
-| **License** | Apache 2.0 |
-
-## Performance
-
-### DharmaOCR-Benchmark Results
+DharmaOCR Lite (3B) **outperforms models with more than twice as many parameters**, including olmOCR-2-7B, and surpasses every commercial API tested.
 
 | Model | Score | Degeneration Rate (%) | Time/Page (s) |
 |---|---|---|---|
-| **DharmaOCR Lite (ours)** | **0.911** | **0.20** | **1.464** |
-| DharmaOCR Full (ours, 7B) | 0.925 | 0.40 | 2.132 |
-| olmOCR-2-7B (vanilla) | 0.823 | 1.41 | 4.306 |
-| Nanonets-OCR2-3B (vanilla) | 0.791 | 2.62 | 1.911 |
+| **DharmaOCR Full** (7B, ours) | **0.925** | 0.40 | 2.132 |
+| **DharmaOCR Lite** (3B, ours) | **0.911** | **0.20** | **1.464** |
 | Claude Opus 4.6 | 0.833 | — | — |
+| Qwen3-VL-8B | 0.829 | 5.65 | 7.250 |
+| olmOCR-2-7B | 0.823 | 1.41 | 4.306 |
 | Gemini 3.1 Pro | 0.820 | — | — |
+| Nanonets-OCR2-3B | 0.791 | 2.62 | 1.911 |
 | GPT-5.4 | 0.750 | — | — |
 | GPT-4o | 0.635 | — | — |
 | Google Document AI | 0.640 | — | — |
 | Amazon Textract | 0.618 | — | — |
+| Mistral OCR 3 | 0.574 | — | — |
 
-> **DharmaOCR Lite (3B) outperforms olmOCR-2-7B (7B)** — a model with more than twice as many parameters — by ~10% in benchmark score, while being ~3× faster and ~66% cheaper per page.
+Score = (LevenshteinRatio + BLEU) / 2, evaluated on [DharmaOCR-Benchmark](https://huggingface.co/datasets/dharma-ai/DharmaOCR-Benchmark) (496 instances covering printed, handwritten, and legal/administrative documents in Brazilian Portuguese). Time/page measured on NVIDIA L40S.
 
-### Benchmark Score Definition
+### Lowest text degeneration rate
 
-The DharmaOCR-Benchmark Score is defined as:
+Text degeneration — where models get stuck in repetitive loops — is a critical but underreported problem in OCR. It's not just a quality issue: **a single degenerate request can nearly double GPU time and cost** for a batch of concurrent requests, reducing throughput for the entire system.
 
-```
-score = (LevenshteinRatio + BLEU) / 2
-```
+DharmaOCR Lite achieves a **0.20% degeneration rate**, the lowest across all 22+ models evaluated (open-source and commercial).
+
+### Competitive cost
 
-where `LevenshteinRatio` captures character-level fidelity and `BLEU` measures n-gram sequence preservation.
+| Model | Score | Relative Cost |
+|---|---|---|
+| **DharmaOCR Lite** (3B) | 0.911 | **34%** |
+| olmOCR-2-7B | 0.823 | 100% (reference) |
+| Qwen3-VL-8B | 0.829 | 168% |
+| Nanonets-OCR2-3B | 0.791 | 44% |
+
+DharmaOCR Lite is **~3× cheaper** than olmOCR-2-7B while scoring ~10% higher. On an H200 GPU with optimized inference settings, cost drops even further.
 
 ## Quickstart
 
 ```python
 from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
 from qwen_vl_utils import process_vision_info
-from PIL import Image
 
 model_name = "dharma-ai/DharmaOCR-Lite"
 
@@ -99,7 +84,6 @@ model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
 )
 processor = AutoProcessor.from_pretrained(model_name)
 
-# Load your document image
 image_path = "document.png"
 
 messages = [
@@ -133,7 +117,7 @@ output_text = processor.batch_decode(
 print(output_text)
 ```
 
-### Expected Output Format
+### Output Format
 
 ```json
 {
@@ -144,7 +128,7 @@ print(output_text)
 }
 ```
 
-Fields that are not present in the original document are returned as `null`.
+Fields not present in the original document are returned as `null`. This lets you decide whether to use auxiliary fields (header, footer, margins) depending on your application.
 
 ## Serving with vLLM
 
@@ -155,43 +139,11 @@ vllm serve dharma-ai/DharmaOCR-Lite \
     --max-num-batched-tokens 32000
 ```
 
-## Training Details
-
-### Pipeline
-
-1. **Supervised Fine-Tuning (SFT):** Full fine-tuning on ~39,680 pages of diverse document types (printed, handwritten, tables, forms, mixed layouts) predominantly in Brazilian Portuguese. Labels were generated by large LLMs (Claude Sonnet 4, Llama 4 Maverick, Gemini 2.5 Pro) and validated by human reviewers.
-
-2. **Direct Preference Optimization (DPO):** A novel application of DPO to OCR — degenerate model outputs were explicitly used as *rejected* examples to penalize looping/repetitive behavior. Preference pairs were constructed from 5 candidate responses per document, scored by Qwen3-VL-235B as judge, and filtered through a multi-stage policy combining Selective-DPO principles and reward-margin analysis. Final dataset: 49,170 preference pairs.
-
-3. **AWQ Quantization (FP8):** Activation-aware weight quantization preserving visual encoder and output layer in full precision. Reduces cost by ~12% with minimal quality degradation (score: 0.921 → 0.911).
-
-### Infrastructure
-
-- **SFT:** 1× NVIDIA H200, 24 CPU cores, 256 GB RAM
-- **DPO:** 4× NVIDIA H200, 96 CPU cores, 1024 GB RAM
-- **Hyperparameters:** Effective batch size 32, AdamW optimizer, cosine LR schedule
-
-## Why DPO for OCR?
-
-Text degeneration — where models get stuck in repetitive loops — is a critical but underreported problem in OCR systems. It's not just a quality issue: degenerate requests consume disproportionate GPU time, reduce throughput for *all* concurrent requests, and inflate costs.
-
-DharmaOCR Lite applies DPO to reduce degeneration by **87.6%** relative to SFT-only training (from 1.61% → 0.20%), the largest reduction observed across all model families tested.
-
-## DharmaOCR-Benchmark
-
-We release [DharmaOCR-Benchmark](https://huggingface.co/datasets/dharma-ai/DharmaOCR-Benchmark), a 496-instance evaluation suite for OCR in Brazilian Portuguese covering:
-
-- **ESTER-Pt** (363 samples): Printed text recognition
-- **Legal** (83 samples): Legal and administrative documents
-- **BRESSAY** (50 samples): Handwritten text recognition
-
-The benchmark evaluates transcription quality, text degeneration rate, and unit inference cost under a unified protocol.
-
 ## Limitations
 
 - **Language focus:** Primarily optimized for Brazilian Portuguese documents. Performance on other languages may vary.
-- **Field repetition:** The model may occasionally repeat header/footer content within the `text` field. A post-processing step checking exact matches resolves >80% of occurrences.
-- **Domain scope:** Best results on printed, handwritten, and legal/administrative documents. Highly specialized layouts (e.g., complex engineering drawings) are not covered.
+- **Field repetition:** The model may occasionally repeat header/footer content within the `text` field. A post-processing step checking exact matches between fields resolves >80% of occurrences.
+- **Domain scope:** Best results on printed, handwritten, and legal/administrative documents.
 
 ## Citation