Model reference · open weights
GOT-OCR2_0 is an open-weight language model from stepfun-ai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
🔋Online Demo | 🌟GitHub | 📜Paper</a Haoran Wei, Chenglong Liu, Jinyue Chen, Jia Wang, Lingyu Kong, Yanming Xu, Zheng Ge, Liang Zhao, Jianjian Sun, Yuang Peng, Chunrui Han, Xiangyu Zhang Usage Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.10： More details about 'ocrtype', 'ocrbox', 'ocrcolor', and 'render' can be found at our GitHub. Our training codes are available at our GitHub. More Multimodal Projects 👏 Welcome to explore more multimodal projects of our team: Vary | Fox | OneChart Citation If you find our work helpful, please consider citing our papers 📝 and liking this project ❤️！
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | stepfun-ai |
|---|---|
| Type | Language models |
| Parameters (lead) | 716M |
| Context | 32k tokens |
| Variants | 1 |
| Released | 2024-09-12 |
| Popularity | 707k downloads / month |
| Likes | 1,557 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| GOT-OCR2_0 | 716M | BF16 | ~1.6 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys got-ocr2-0 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (got-ocr2-0 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"got-ocr2-0","messages":[{"role":"user","content":"Hello"}]}'
Details
Languages
Tags
Papers
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗