Model reference · open weights
trocr-small-korean is an open-weight language model from team-lucid. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | team-lucid |
|---|---|
| Type | Language models |
| Task | Image→text |
| Parameters (lead) | 55M |
| Runs with | transformers |
| Released | 2023-06-30 |
| Popularity | 1k downloads / month |
| Licence | Open weights |
About
TrOCR은 Encoder-Decoder 모델로, 이미지 트랜스포머 인코더와 텍스트 트랜스포머 디코더로 이루어져 있습니다. 이미지 인코더는 DeiT 가중치로 초기화되었고, 텍스트 디코더는 자체적으로 학습한 RoBERTa 가중치로 초기화되었습니다.
이 연구는 구글의 TPU Research Cloud(TRC)를 통해 지원받은 Cloud TPU로 학습되었습니다.
import torch
from transformers import VisionEncoderDecoderModel
model = VisionEncoderDecoderModel.from_pretrained("team-lucid/trocr-small-korean")
pixel_values = torch.rand(1, 3, 384, 384)
generated_ids = model.generate(pixel_values)
해당 모델은 synthtiger로 합성된 6M개의 이미지로 학습되었습니다
| Hyperparameter | Small |
|---|---|
| Warmup Steps | 4,000 |
| Learning Rates | 1e-4 |
| Batch Size | 512 |
| Weight Decay | 0.01 |
| Max Steps | 500,000 |
| Learning Rate Decay | 0.1 |
| \(Adam\beta_1\) | 0.9 |
| \(Adam\beta_2\) | 0.98 |
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys trocr-small-korean for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (trocr-small-korean 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":"trocr-small-korean","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.