Image-Text-to-Text
Transformers
Joblib
Safetensors
nemotron_parse
text-generation
document-parsing
ocr
tables
charts
ground-truth-sft
grpo
verifiable-rewards
routed-refinement
thrisul
conversational
custom_code
Instructions to use sandeeprdy1729/thrisul-parser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sandeeprdy1729/thrisul-parser with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="sandeeprdy1729/thrisul-parser", trust_remote_code=True) messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("sandeeprdy1729/thrisul-parser", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use sandeeprdy1729/thrisul-parser with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sandeeprdy1729/thrisul-parser" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sandeeprdy1729/thrisul-parser", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/sandeeprdy1729/thrisul-parser
- SGLang
How to use sandeeprdy1729/thrisul-parser with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "sandeeprdy1729/thrisul-parser" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sandeeprdy1729/thrisul-parser", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "sandeeprdy1729/thrisul-parser" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sandeeprdy1729/thrisul-parser", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use sandeeprdy1729/thrisul-parser with Docker Model Runner:
docker model run hf.co/sandeeprdy1729/thrisul-parser
benchmarks update (v1): ParseBench/olmOCR-Bench measured sections
Browse files
README.md
CHANGED
|
@@ -51,6 +51,37 @@ final policy. Every P0 defect found in the v1 audit is addressed; the audit trai
|
|
| 51 |
- Real financial tables from FinTabNet.c (`bsmock/FinTabNet.c`, HTML ground truth, CDLA-Permissive-2.0).
|
| 52 |
- Compute: Kaggle free tier (T4), LoRA, 1583 SFT optimizer steps + 303 GRPO groups. Targets: 6330 (~533 tokens mean).
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
## Results (read the caveats)
|
| 55 |
All numbers below were measured by us on **held-out synthetic data and a seeded ParseBench-proxy sample on a T4 with Transformers** (no vLLM).
|
| 56 |
They are **not** the official ParseBench score and are **not comparable** to H100/vLLM numbers anywhere below. Headline deltas carry bootstrap 95% CIs.
|
|
|
|
| 51 |
- Real financial tables from FinTabNet.c (`bsmock/FinTabNet.c`, HTML ground truth, CDLA-Permissive-2.0).
|
| 52 |
- Compute: Kaggle free tier (T4), LoRA, 1583 SFT optimizer steps + 303 GRPO groups. Targets: 6330 (~533 tokens mean).
|
| 53 |
|
| 54 |
+
<!-- THRISUL-BENCH:BEGIN -->
|
| 55 |
+
## Official benchmark results (thrisul-parser)
|
| 56 |
+
|
| 57 |
+
Measured 2026-10-31 on Kaggle 2×T4 (Transformers, fp16, greedy) by this benchmark notebook. Run tag: `v1`. Coverage: ParseBench 60 pages/dimension (official total 2,078) · olmOCR-Bench 105 pages (official total = all unique bench pages) · OmniDocBench: packaged · NVIDIA suites: IndicVisionBench=pending, MOSCAR=pending.
|
| 58 |
+
|
| 59 |
+
> Sampling disclosure: these runs cover a **seeded stratified subset** unless the config covered every page. Partial coverage is labeled — never quoted as the full-suite official score. Base-model deltas on identical pages are in `results.json`.
|
| 60 |
+
|
| 61 |
+
### ParseBench (official evaluator, sampled)
|
| 62 |
+
|
| 63 |
+
| group | score |
|
| 64 |
+
|---|---|
|
| 65 |
+
| chart | 0.206 |
|
| 66 |
+
| table | 0.168 |
|
| 67 |
+
| text_formatting | 0.037 |
|
| 68 |
+
| text_content | 0.491 |
|
| 69 |
+
| text | 0.091 |
|
| 70 |
+
| overall_rule_avg | 0.145 |
|
| 71 |
+
| **mean of table/chart/text** | **0.155** |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Published context (ParseBench leaderboard head, self-reported)
|
| 75 |
+
|
| 76 |
+
- LlamaParse Cost Effective: 78.02
|
| 77 |
+
- LlamaParse Agentic: 83.07
|
| 78 |
+
- LlamaParse Agentic Plus: 86.61
|
| 79 |
+
- OpenAI GPT-5 Mini (Reasoning Minimal): 46.83
|
| 80 |
+
- OpenAI GPT-5 Mini (Reasoning Medium): 51.52
|
| 81 |
+
- Anthropic Haiku 4.5 (Disable Thinking): 45.17
|
| 82 |
+
- Anthropic Haiku 4.5 (Thinking): 53.12
|
| 83 |
+
- Google Gemini 3 Flash (Thinking Minimal): 71.04
|
| 84 |
+
<!-- THRISUL-BENCH:END -->
|
| 85 |
## Results (read the caveats)
|
| 86 |
All numbers below were measured by us on **held-out synthetic data and a seeded ParseBench-proxy sample on a T4 with Transformers** (no vLLM).
|
| 87 |
They are **not** the official ParseBench score and are **not comparable** to H100/vLLM numbers anywhere below. Headline deltas carry bootstrap 95% CIs.
|