Image-to-Text
Transformers
Safetensors
English
vision-encoder-decoder
image-text-to-text
chess
ocr
handwritten-text-recognition
trocr
computer-vision
Instructions to use uchihamadara1816/TROCR-Chess with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use uchihamadara1816/TROCR-Chess with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="uchihamadara1816/TROCR-Chess")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("uchihamadara1816/TROCR-Chess") model = AutoModelForMultimodalLM.from_pretrained("uchihamadara1816/TROCR-Chess", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "bos_token_id": 0, | |
| "early_stopping": true, | |
| "eos_token_id": [ | |
| 2 | |
| ], | |
| "max_new_tokens": 16, | |
| "num_beams": 4, | |
| "pad_token_id": 1, | |
| "transformers_version": "4.57.3" | |
| } | |