# PaddleOCR-VL-1.6 by PaddlePaddle: Open-Weight Model Source: https://savrn.com/models/paddleocr-vl-1-6 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve PaddleOCR-VL-1.6 (959M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 1.9 GB | 2.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 1.0 GB | 1.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.5 GB | 0.6 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 23, 2026. [PaddleOCR-VL-1.6 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/paddleocr-vl-1-6/gpus) ## SAVRN's Notes on PaddleOCR-VL-1.6 PaddleOCR-VL 1.6 parses documents, including text, tables, formulas and charts, with a compact model of under 1B parameters. It builds on version 1.5 with better handling of difficult page regions. It needs about 2 GB at 16-bit, so it can run on nearly any GPU. Apache 2.0 allows commercial use. For high-volume document parsing where cost per page matters, this is one of the first models we would test. SAVRN Research, 2026-09-18 ## Model Card By PaddlePaddle, published under apache-2.0, revision c5630abae1d9. ### PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training [![repo](https://img.shields.io/github/stars/PaddlePaddle/PaddleOCR?color=ccf)](https://github.com/PaddlePaddle/PaddleOCR) [![HuggingFace](https://img.shields.io/badge/HuggingFace-black.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.6) [![ModelScope](https://img.shields.io/badge/ModelScope-black?logo=data:image/svg+xml;base64,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&labelColor=white)](https://modelscope.cn/models/PaddlePaddle/PaddleOCR-VL-1.6) [![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-black.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/PaddlePaddle/PaddleOCR-VL-1.6_Online_Demo) [![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-black?logo=data:image/svg+xml;base64,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&labelColor=white)](https://modelscope.cn/studios/PaddlePaddle/PaddleOCR-VL-1.6_Online_Demo/summary) [![Discord](https://img.shields.io/badge/Discord-ERNIE-5865F2?logo=discord&logoColor=white)](https://discord.gg/JPmZXDsEEK) [![X](https://img.shields.io/badge/X-PaddlePaddle-6080F0)](https://x.com/PaddlePaddle) [![License](https://img.shields.io/badge/license-Apache_2.0-green)](./LICENSE) ** [Official Website](https://www.paddleocr.com)** ** [Technical Report](https://arxiv.org/pdf/2606.03264)** ### Introduction We introduce PaddleOCR-VL-1.6, an upgraded compact document parsing model built upon PaddleOCR-VL-1.5. PaddleOCR-VL-1.6 introduces a region-aware data optimization framework that identifies weak regions from the previous model, applies targeted enhancement to those regions, and improves the reliability of supervision signals. It further adopts a progressive post-training recipe based on curated data selection and reinforcement learning, pushing model performance to a higher level through staged optimization. PaddleOCR-VL-1.6 achieves a new state-of-the-art score of 96.33% on OmniDocBench v1.6, sets new records on OmniDocBench v1.5 and Real5-OmniDocBench as well, and demonstrates strong competitiveness against top-tier VLMs. The model architecture is fully compatible with PaddleOCR-VL-1.5, enabling zero-cost plug-and-play migration. #### Key Capabilities of PaddleOCR-VL-1.6 [Read the full model card (1,031 words)](https://savrn.com/models/paddleocr-vl-1-6/card) ## Configuration Architecture PaddleOCRVLForConditionalGeneration Context length (tokens) 131,072 Layers 18 Hidden size 1,024 Feed-forward size 3,072 Attention heads 16 Key/value heads 2 Head dimension 128 Vocabulary size 103,424 RoPE base 500,000 Stored precision bfloat16 Model type paddleocr_vl ## Identity and Version Repository PaddlePaddle/PaddleOCR-VL-1.6 Publisher PaddlePaddle Task Image and text to text Modality Image and text Library PaddleOCR Parameters 959M parameters Languages en, zh Revision c5630abae1d940eafe0697512a0325494b02ab42 First published 2026-05-27 Last updated 2026-08-08 ## Files and Weights 20 files, 1.9 GB in total. The weights are 1 file totalling 1.9 GB in safetensors. Weights1 file · 1.9 GB Configuration12 files · 180.2 KB Tokenizer3 files · 13.0 MB Documentation2 files · 32.8 KB Other1 file · 1.5 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 1.9 GB | 85a479d506a1 | | .eval_results/real5_omnidocbench.yaml | Configuration | 1.4 KB | — | | added_tokens.json | Configuration | 25.4 KB | — | | config.json | Configuration | 2.1 KB | — | | configuration_paddleocr_vl.py | Configuration | 8.1 KB | — | | generation_config.json | Configuration | 133 B | — | | image_processing_paddleocr_vl.py | Configuration | 25.0 KB | — | | inference.yml | Configuration | 43 B | — | | modeling_paddleocr_vl.py | Configuration | 103.9 KB | — | | preprocessor_config.json | Configuration | 641 B | — | | processing_paddleocr_vl.py | Configuration | 12.3 KB | — | | processor_config.json | Configuration | 137 B | — | | special_tokens_map.json | Configuration | 1.2 KB | — | | LICENSE | Documentation | 11.4 KB | — | | README.md | Documentation | 21.4 KB | — | | chat_template.jinja | Other | 1.5 KB | — | | .gitattributes | Repository | 1.6 KB | — | | tokenizer.json | Tokenizer | 11.2 MB | c8a215a59183 | | tokenizer.model | Tokenizer | 1.6 MB | 34ef7db83df7 | | tokenizer_config.json | Tokenizer | 186.9 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 1.9 GB [Download from PaddlePaddle](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.6) Released by PaddlePaddle through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by arXiv:2606.03264 ## Evaluations Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical. | Benchmark | Conditions | Result | Reported by | Revision | Date | | --- | --- | --- | --- | --- | --- | | Delores-Lin/MDPBench | Task arMetric arComparison conditions not established | 76.2 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task deMetric deComparison conditions not established | 85.1 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task digitalMetric digitalComparison conditions not established | 87.1 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task enMetric enComparison conditions not established | 83.5 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task esMetric esComparison conditions not established | 75.1 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task frMetric frComparison conditions not established | 78.6 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task hiMetric hiComparison conditions not established | 70.7 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task idMetric idComparison conditions not established | 82.7 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task itMetric itComparison conditions not established | 85.5 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task jpMetric jpComparison conditions not established | 70.3 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task koMetric koComparison conditions not established | 86.3 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task latinMetric latinComparison conditions not established | 81.4 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task nlMetric nlComparison conditions not established | 80.5 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task non_latinMetric non_latinComparison conditions not established | 76.1 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task overallMetric overallComparison conditions not established | 78.9 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task photographedMetric photographedComparison conditions not established | 76.3 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task privateMetric privateComparison conditions not established | 83 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task ptMetric ptComparison conditions not established | 80.9 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task thMetric thComparison conditions not established | 67.3 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task zhMetric zhComparison conditions not established | 85.9 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | Delores-Lin/MDPBench | Task zh_tMetric zh_tComparison conditions not established | 76.7 | [MDPBench leaderboard](https://huggingface.co/datasets/Delores-Lin/MDPBench) Reported by a third party | Evaluated revision not stated | 2026-08-15 | | PaddlePaddle/Real5-OmniDocBench | Task illuminationMetric illuminationComparison conditions not established | 93.28 | [Real5-OmniDocBench Leaderboard](https://huggingface.co/datasets/PaddlePaddle/Real5-OmniDocBench) Reported by a third party | Evaluated revision not stated | 2026-08-08 | | PaddlePaddle/Real5-OmniDocBench | Task overallMetric overallComparison conditions not established | 93.19 | [Real5-OmniDocBench Leaderboard](https://huggingface.co/datasets/PaddlePaddle/Real5-OmniDocBench) Reported by a third party | Evaluated revision not stated | 2026-08-08 | | PaddlePaddle/Real5-OmniDocBench | Task scanningMetric scanningComparison conditions not established | 94.74 | [Real5-OmniDocBench Leaderboard](https://huggingface.co/datasets/PaddlePaddle/Real5-OmniDocBench) Reported by a third party | Evaluated revision not stated | 2026-08-08 | | PaddlePaddle/Real5-OmniDocBench | Task screen_photographyMetric screen_photographyComparison conditions not established | 92.78 | [Real5-OmniDocBench Leaderboard](https://huggingface.co/datasets/PaddlePaddle/Real5-OmniDocBench) Reported by a third party | Evaluated revision not stated | 2026-08-08 | | PaddlePaddle/Real5-OmniDocBench | Task skewMetric skewComparison conditions not established | 92.66 | [Real5-OmniDocBench Leaderboard](https://huggingface.co/datasets/PaddlePaddle/Real5-OmniDocBench) Reported by a third party | Evaluated revision not stated | 2026-08-08 | | PaddlePaddle/Real5-OmniDocBench | Task warpingMetric warpingComparison conditions not established | 92.48 | [Real5-OmniDocBench Leaderboard](https://huggingface.co/datasets/PaddlePaddle/Real5-OmniDocBench) Reported by a third party | Evaluated revision not stated | 2026-08-08 | | allenai/olmOCR-bench | Task old_scansMetric old_scansSetup PaddleOCR-VL-1.6 pipeline, greedy, no tuning; old_scans.jsonl sub-scoreComparison conditions not established | 38.6 | [ocr-bench — old_scans eval](https://github.com/davanstrien/ocr-bench/tree/d07a41232/experiments/olmocr-bench-oldscans) Reported by a third party | Evaluated revision not stated | 2026-06-27 | | llamaindex/ParseBench | Task chartMetric chartSetup Pipeline name: paddleocr_vl_1_6_pipelineComparison conditions not established | 54.24 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-06-01 | | llamaindex/ParseBench | Task layoutMetric layoutSetup Pipeline name: paddleocr_vl_1_6_pipelineComparison conditions not established | 77.8 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-06-01 | | llamaindex/ParseBench | Task meanMetric meanSetup Pipeline name: paddleocr_vl_1_6_pipelineComparison conditions not established | 67.43 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-06-01 | | llamaindex/ParseBench | Task tableMetric tableSetup Pipeline name: paddleocr_vl_1_6_pipelineComparison conditions not established | 67.77 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-06-01 | | llamaindex/ParseBench | Task text_contentMetric text_contentSetup Pipeline name: paddleocr_vl_1_6_pipelineComparison conditions not established | 82.71 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-06-01 | | llamaindex/ParseBench | Task text_formattingMetric text_formattingSetup Pipeline name: paddleocr_vl_1_6_pipelineComparison conditions not established | 54.64 | [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) Reported by a third party | Evaluated revision not stated | 2026-06-01 | ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 1.9 GB | | 16-bit | 1.9 GB | | 8-bit | 1.0 GB | | 4-bit | 0.5 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Compare PaddleOCR-VL-1.6 - [PaddleOCR-VL-1.6 vs Qwen3.5-0.8B](https://savrn.com/models/compare/paddleocr-vl-1-6-vs-qwen3-5-0-8b) ## Questions About PaddleOCR-VL-1.6 ### How much GPU memory does PaddleOCR-VL-1.6 need? About 2.3 GB at 16-bit and 0.6 GB at 4-bit: the weights (959M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run PaddleOCR-VL-1.6 on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use PaddleOCR-VL-1.6 commercially? Yes. PaddleOCR-VL-1.6 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is PaddleOCR-VL-1.6's context length? 131,072 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Image and text to text ### [PaddleOCR-VL-1.5](https://savrn.com/models/paddleocr-vl-1-5) [PaddlePaddle](https://savrn.com/model-publishers/paddlepaddle) PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing PaddleOCR-VL-1.5 is an advanced next-generation model of PaddleOCR-VL, achieving a new state-of-the-art accuracy of 94.5% on OmniDocBench v1.5. To rigorously evaluate robustness against real-world physical distortions—including scanning artifacts, skew, warping, screen photography, and illumination—we propose the Real5-OmniDocBench benchmark. Experimental results demonstrate that this enhanced model attains SOTA performance on the newly curated benchmark. Furthermore, we extend the model’s capabilities by incorporating seal recognition and text spotting tasks, while remaining a 0.9B ultra-compact VLM… Open weights apache-2.0 959M parameters 131,072 tokens PaddleOCR [View model](https://savrn.com/models/paddleocr-vl-1-5) Model · Image and text to text ### [povl-opd-scale05](https://savrn.com/models/povl-opd-scale05) [Cheney Wong](https://savrn.com/model-publishers/cheneywong) On-policy distillation. The weight delta learned by the teacher was merged into the SFT base with an extra scale of 0.5, the best point of an alpha sweep (0.25 -> +0.32, 0.5 -> +0.44, 0.75 -> -0.29, 1.5 -> -3.01 with t = -12.42). Fine-tuned from CheneyWong/povl-sft-2d-merge, which is NOT the RL checkpoint -- the teacher delta was merged into the SFT base, which is why it neither clearly beats nor clearly follows round 2. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly… Open weights apache-2.0 906M parameters 131,072 tokens transformers [View model](https://savrn.com/models/povl-opd-scale05) Model · Image and text to text ### [povl-rl-gsapo-200](https://savrn.com/models/povl-rl-gsapo-200) [Cheney Wong](https://savrn.com/model-publishers/cheneywong) Reinforcement learning round 2, GSAPO, 200 steps. The delivered model of that round. Equal-weight TEDS 0.8473 / TEDS-Struct 0.9078 over 33,545 samples. Fine-tuned from CheneyWong/povl-rl-dapo-400, which is RL round 1 -- the stages form a single linear chain. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly reads the visible text scores 0.33 TEDS / 1.00 TEDS-S. Only the TEDS-S column is meaningful for that dataset. Rejected at the gate. The one substantive gap: every… Open weights apache-2.0 906M parameters 131,072 tokens transformers [View model](https://savrn.com/models/povl-rl-gsapo-200) Model · Image and text to text ### [povl-rl-dapo-400](https://savrn.com/models/povl-rl-dapo-400) [Cheney Wong](https://savrn.com/model-publishers/cheneywong) Reinforcement learning round 1, DAPO algorithm, 400 steps. Fine-tuned from CheneyWong/povl-dpo-2ep, which is its own immediate predecessor in the same run. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly reads the visible text scores 0.33 TEDS / 1.00 TEDS-S. Only the TEDS-S column is meaningful for that dataset. Only works with DAPO's dynamic sampling. The first attempt with GSAPO had 78% of groups contributing zero gradient (49.0% saturated, 16.5% identical rewards, 12.6%… Open weights apache-2.0 906M parameters 131,072 tokens transformers [View model](https://savrn.com/models/povl-rl-dapo-400) Model · Image and text to text ### [povl-dpo-2ep](https://savrn.com/models/povl-dpo-2ep) [Cheney Wong](https://savrn.com/model-publishers/cheneywong) Direct preference optimisation on top of the corrective SFT, 2 epochs over 8,383 preference pairs. Intended to move the model from 'roughly right structure' to 'exactly right structure'. Fine-tuned from CheneyWong/povl-sft-2d-merge, which is its own immediate predecessor in the same run. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a perturbation test shows a structurally perfect prediction that correctly reads the visible text scores 0.33 TEDS / 1.00 TEDS-S. Only the TEDS-S column is meaningful for that dataset. The gain is within sampling… Open weights apache-2.0 906M parameters 131,072 tokens transformers [View model](https://savrn.com/models/povl-dpo-2ep) Model · Image and text to text ### [povl-sft-2d-merge](https://savrn.com/models/povl-sft-2d-merge) [Cheney Wong](https://savrn.com/model-publishers/cheneywong) Corrective supervised fine-tuning. The core fix is the two-dimensional merge token (a cell spanning both rows and columns): it accounted for only 0.89% of cell tokens in the previous training mixture, and one source had 0.00%. 22,110 samples with two or more 2D merges were added, lifting the rate to 3.92% (1.06 -> 4.96 per table). This also eliminated the runaway-truncation failure mode entirely. Fine-tuned from CheneyWong/povl-sft-full-3ep, which is its own immediate predecessor in the same run. Base = the unmodified base model. Public datasets only; the project's self-built benchmarks are excluded. (~0.22 here) measures how well the model reproduces empty cells and should be ignored -- a… Open weights apache-2.0 906M parameters 131,072 tokens transformers [View model](https://savrn.com/models/povl-sft-2d-merge) ## PaddlePaddle [All models and datasets](https://savrn.com/model-publishers/paddlepaddle) ## Versions - [c5630abae1d9](https://savrn.com/models/paddleocr-vl-1-6/versions/c5630abae1d9) · current 2026-09-18 ## Explore More - [All image and text to text models](https://savrn.com/models/tasks/image-and-text-to-text) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [Hugging Face record](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.6) - [How the hub is built](https://savrn.com/model-hub/methodology)