CharlZKP/OpenThai2.0-OCR-Markdown-ONNX
image-text-to-text model by CharlZKP
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
An ONNX export of iapp/OpenThai2.0-OCR-Markdown (iApp Technology's Thai fine-tune of NVIDIA Nemotron 3.5 Parse) for onnxruntime-web, WebGPU or WASM, so pages are read entirely on the user's device. The weights are not quantized. Every tensor is the original float32 value from model.safetensors, copied byte for byte. The graphs are rewritten so that the browser runtime can run them. Nothing was retrained or pruned. Interfaces: Preprocessing matches NemotronParseImageProcessor (navit packing): fit inside 1664×2048 with a PIL bilinear downscale, pad right and bottom with white to height%16 and width%64, then the CLIP mean/std. The prompt is = ids [2, 0, 50004, 50008, 50001, 50009]. Decoding is greedy with repetition penalty 1.1 (generationconfig.json) and stops at (id…
Read the full model card ↗ · Preview checked 2026-11-13T07:38:27.547Z
Inside the original model card — Document outline
- OpenThai2.0-OCR-Markdown, ONNX for the browser (fp32)
- Files (onnx/)
- Parity with the original (Transformers, fp32, CPU)
- Licence and attribution
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
CharlZKP/OpenThai2.0-OCR-Markdown-ONNX is a image-text-to-text model repository published by CharlZKP on Hugging Face. The source reports the onnxruntime library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- onnxruntime
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- RadioMBartPrefixForCausalLM
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-11-13T06:47:57.000Z
- Last modified
- 2026-11-13T06:48:54.000Z
Compatibility and lineage
Reported languages: th, en
Reported base models: iapp/OpenThai2.0-OCR-Markdown
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-13T06:57:58.356Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.