Instructions to use ManBib/trocr-large-printed-im2latex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ManBib/trocr-large-printed-im2latex with Transformers:

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

pipe = pipeline("image-text-to-text", model="ManBib/trocr-large-printed-im2latex")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("ManBib/trocr-large-printed-im2latex")
model = AutoModelForImageTextToText.from_pretrained("ManBib/trocr-large-printed-im2latex")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ManBib/trocr-large-printed-im2latex with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ManBib/trocr-large-printed-im2latex"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ManBib/trocr-large-printed-im2latex",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ManBib/trocr-large-printed-im2latex

SGLang

How to use ManBib/trocr-large-printed-im2latex 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 "ManBib/trocr-large-printed-im2latex" \
    --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": "ManBib/trocr-large-printed-im2latex",
		"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 "ManBib/trocr-large-printed-im2latex" \
        --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": "ManBib/trocr-large-printed-im2latex",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ManBib/trocr-large-printed-im2latex with Docker Model Runner:
```
docker model run hf.co/ManBib/trocr-large-printed-im2latex
```

ManBib commited on Feb 17, 2024

Commit

e40d5cb

verified ·

1 Parent(s): e4e646c

Model save

Browse files

Files changed (1) hide show

README.md +5 -3

README.md CHANGED Viewed

@@ -33,11 +33,13 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 8
-- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 2
 ### Training results

 The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 8
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: inverse_sqrt
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 5
+- mixed_precision_training: Native AMP
 ### Training results