Instructions to use kingabzpro/t5gemma2-latex-ocr-1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kingabzpro/t5gemma2-latex-ocr-1k with Transformers:

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

pipe = pipeline("image-text-to-text", model="kingabzpro/t5gemma2-latex-ocr-1k")

# Load model directly
from transformers import AutoProcessor, AutoModelForSeq2SeqLM

processor = AutoProcessor.from_pretrained("kingabzpro/t5gemma2-latex-ocr-1k")
model = AutoModelForSeq2SeqLM.from_pretrained("kingabzpro/t5gemma2-latex-ocr-1k")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kingabzpro/t5gemma2-latex-ocr-1k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingabzpro/t5gemma2-latex-ocr-1k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kingabzpro/t5gemma2-latex-ocr-1k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kingabzpro/t5gemma2-latex-ocr-1k

SGLang

How to use kingabzpro/t5gemma2-latex-ocr-1k 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 "kingabzpro/t5gemma2-latex-ocr-1k" \
    --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": "kingabzpro/t5gemma2-latex-ocr-1k",
		"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 "kingabzpro/t5gemma2-latex-ocr-1k" \
        --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": "kingabzpro/t5gemma2-latex-ocr-1k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kingabzpro/t5gemma2-latex-ocr-1k with Docker Model Runner:
```
docker model run hf.co/kingabzpro/t5gemma2-latex-ocr-1k
```

t5gemma2-latex-ocr-1k

This model is a fine-tuned version of google/t5gemma-2-270m-270m on an unknown dataset.

Usage

from transformers import pipeline

generator = pipeline(
    "image-text-to-text",
    model="kingabzpro/t5gemma2-latex-ocr-1k",
)

generator(
    val_ds[10]["image"],
    text="<start_of_image> Convert this image to LaTeX. Output only LaTeX.",
    generate_kwargs={"do_sample": False, "max_new_tokens": 100},
)

Output:

[{'input_text': '<start_of_image> Convert this image to LaTeX. Output only LaTeX.',
  'generated_text': '<start_of_image> Convert this image to LaTeX. Output only LaTeX.f ( p , p ^ { \\prime } ) = \\ln \\left\\{ \\begin{array} { \\begin{array} { \\begin{array} { \\begin{array} { \\begin{array} { \\end{array} \\right\\} \\begin{array} { \\begin{array} { \\begin{array} { \\end{array} \\right\\} \\begin{array} { \\begin{array} { \\begin{array} {'}]

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 15
num_epochs: 1

Framework versions

Transformers 5.0.0rc1
Pytorch 2.8.0+cu128
Datasets 4.4.2
Tokenizers 0.22.1

Downloads last month: 8

Safetensors

Model size

0.8B params

Tensor type

BF16

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kingabzpro/t5gemma2-latex-ocr-1k

Base model

google/t5gemma-2-270m-270m

Finetuned

(9)

this model

kingabzpro
/

t5gemma2-latex-ocr-1k

t5gemma2-latex-ocr-1k

Usage

Training hyperparameters

Framework versions

Model tree for kingabzpro/t5gemma2-latex-ocr-1k

Dataset used to train kingabzpro/t5gemma2-latex-ocr-1k