Download reference/parse_3_5/validation.json from iapp/OpenThai2.0-OCR-Markdown: direct link, hf CLI and curl.
- Browser
- Download file 3.07 kB
-
https://huggingface.co/iapp/OpenThai2.0-OCR-Markdown/resolve/main/reference/parse_3_5/validation.json
- Command line
-
hf download hf://iapp/OpenThai2.0-OCR-Markdown/reference/parse_3_5/validation.json
-
curl -L -o validation.json https://huggingface.co/iapp/OpenThai2.0-OCR-Markdown/resolve/main/reference/parse_3_5/validation.json
3.07 kB
| { | |
| "status": "scored_and_verified", | |
| "scope": "Fresh quick20/full500 predictions and released Table-body conversion", | |
| "model": "nvidia/Nemotron-3.5-Parse", | |
| "model_revision": "dca5b2df89d00a671509204501d8f1f379d5e94f", | |
| "model_safetensors_sha256": "81dd7609c589f3694ce75520c25af5010953231358de6aec4d03e8c6aac787e9", | |
| "package_version": "3.5.0.post7", | |
| "scheduler": { | |
| "job_id": 7482504, | |
| "state": "COMPLETED", | |
| "exit_code": "0:0" | |
| }, | |
| "runtime": { | |
| "gpu": "NVIDIA H100 80GB HBM3", | |
| "gpu_count": 1, | |
| "dtype": "bfloat16", | |
| "vllm": "0.26.0", | |
| "transformers": "5.14.1", | |
| "huggingface_hub": "1.24.0", | |
| "pillow": "12.3.0", | |
| "dependency_lock_reproduction": false, | |
| "deviation": "Measured serving container used Pillow 12.3.0; source package pins 12.2.0." | |
| }, | |
| "generation": { | |
| "prompt": "</s><s><predict_bbox><predict_classes><output_markdown><predict_text_in_pic>", | |
| "concurrency": 128, | |
| "warmup_count": 16, | |
| "preload_images": true, | |
| "temperature": 0, | |
| "repetition_penalty": 1.1, | |
| "max_tokens": 8744, | |
| "max_model_len": 16384, | |
| "max_num_seqs": 192, | |
| "max_num_batched_tokens": 16384, | |
| "prefix_caching": false, | |
| "one_token_mtp": true, | |
| "attention": "FA3, automatic compatible scheduler", | |
| "coordinate_frame": "content_normalized" | |
| }, | |
| "scoring": { | |
| "version": 3, | |
| "table_mode": "released", | |
| "conversion": "nemotron_parse.postprocessing.postprocess_text(Table,table_format=HTML,PostprocessOptions(render_charts=False))", | |
| "ground_truth_changed": false, | |
| "geometry_changed": false, | |
| "non_table_blocks_changed": false, | |
| "malformed_outputs": "retained" | |
| }, | |
| "regression": { | |
| "quick20": { | |
| "pages": 20, | |
| "request_errors": 0, | |
| "finish_reasons": { | |
| "length": 1, | |
| "stop": 19 | |
| }, | |
| "table_conversion": { | |
| "changed_blocks": 13, | |
| "pages_with_predicted_tables": 10, | |
| "table_blocks": 14, | |
| "unconverted_latex_blocks": 1 | |
| } | |
| }, | |
| "full500": { | |
| "pages": 500, | |
| "request_errors": 0, | |
| "finish_reasons": { | |
| "length": 19, | |
| "stop": 481 | |
| }, | |
| "table_conversion": { | |
| "changed_blocks": 364, | |
| "pages_with_predicted_tables": 255, | |
| "table_blocks": 375, | |
| "unconverted_latex_blocks": 2 | |
| } | |
| } | |
| }, | |
| "verification": [ | |
| { | |
| "split": "quick20", | |
| "pages": 20, | |
| "matches_measured_metrics_and_every_page": true, | |
| "tolerance": 1e-12 | |
| }, | |
| { | |
| "split": "full500", | |
| "pages": 500, | |
| "matches_measured_metrics_and_every_page": true, | |
| "tolerance": 1e-12 | |
| } | |
| ], | |
| "limitations": [ | |
| "Full500 is a lightweight regression harness, not official OmniDocBench TEDS or ParseBench.", | |
| "Token-capped predictions and 2 unconverted malformed Table bodies are retained.", | |
| "Timing excludes preload, warmup, startup, conversion, and scoring.", | |
| "Historical inference.constraints.txt and transformers.constraints.txt describe the older rc3 validation; they are not locks for this measured environment." | |
| ] | |
| } | |