Instructions to use singtan/trocr-devanagari with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use singtan/trocr-devanagari with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="singtan/trocr-devanagari")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("singtan/trocr-devanagari")
model = AutoModelForImageTextToText.from_pretrained("singtan/trocr-devanagari")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use singtan/trocr-devanagari with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "singtan/trocr-devanagari"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "singtan/trocr-devanagari",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/singtan/trocr-devanagari

SGLang

How to use singtan/trocr-devanagari 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 "singtan/trocr-devanagari" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "singtan/trocr-devanagari",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "singtan/trocr-devanagari" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "singtan/trocr-devanagari",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use singtan/trocr-devanagari with Docker Model Runner:
```
docker model run hf.co/singtan/trocr-devanagari
```

trocr-devanagari / README.md

singtan

solvrays/trocr-devanagari-model

624a629 verified 9 months ago

preview code

raw

history blame contribute delete

1.26 kB

	---
	library_name: transformers
	license: mit
	base_model: microsoft/trocr-base-handwritten
	tags:
	- generated_from_trainer
	model-index:
	- name: trocr-devanagari
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# trocr-devanagari

	This model is a fine-tuned version of [microsoft/trocr-base-handwritten](https://huggingface.co/microsoft/trocr-base-handwritten) on the None dataset.

	## Model description

	More information needed

	## Intended uses & limitations

	More information needed

	## Training and evaluation data

	More information needed

	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 0.0005
	- train_batch_size: 64
	- eval_batch_size: 32
	- seed: 42
	- gradient_accumulation_steps: 2
	- total_train_batch_size: 128
	- optimizer: Use OptimizerNames.ADAFACTOR and the args are:
	No additional optimizer arguments
	- lr_scheduler_type: linear
	- num_epochs: 3
	- mixed_precision_training: Native AMP

	### Training results



	### Framework versions

	- Transformers 4.55.0
	- Pytorch 2.8.0+cu128
	- Datasets 4.0.0
	- Tokenizers 0.21.2