Instructions to use lbin2021/my-lecture-ocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lbin2021/my-lecture-ocr with Transformers:

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

pipe = pipeline("image-text-to-text", model="lbin2021/my-lecture-ocr")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("lbin2021/my-lecture-ocr")
model = AutoModelForMultimodalLM.from_pretrained("lbin2021/my-lecture-ocr", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lbin2021/my-lecture-ocr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lbin2021/my-lecture-ocr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lbin2021/my-lecture-ocr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lbin2021/my-lecture-ocr

SGLang

How to use lbin2021/my-lecture-ocr 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 "lbin2021/my-lecture-ocr" \
    --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": "lbin2021/my-lecture-ocr",
		"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 "lbin2021/my-lecture-ocr" \
        --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": "lbin2021/my-lecture-ocr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lbin2021/my-lecture-ocr with Docker Model Runner:
```
docker model run hf.co/lbin2021/my-lecture-ocr
```

my-lecture-ocr

This model is a fine-tuned version of lbin2021/my-lecture-ocr on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3525
Cer: 0.7297

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: 3e-05
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
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
No log	0.16	200	0.6003	0.7381
No log	0.32	400	0.5825	0.7400
0.6879	0.48	600	0.5637	0.7371
0.6879	0.64	800	0.5127	0.7365
0.6150	0.8	1000	0.4855	0.7378
0.6150	0.96	1200	0.4794	0.7356
0.6150	1.12	1400	0.4669	0.7323
0.5016	1.28	1600	0.4416	0.7343
0.5016	1.44	1800	0.4361	0.7324
0.4392	1.6	2000	0.4196	0.7301
0.4392	1.76	2200	0.4000	0.7355
0.4392	1.92	2400	0.3955	0.7314
0.3985	2.08	2600	0.3870	0.7303
0.3985	2.24	2800	0.3801	0.7298
0.3166	2.4	3000	0.3731	0.7305
0.3166	2.56	3200	0.3604	0.7299
0.3166	2.7200	3400	0.3553	0.7316
0.2999	2.88	3600	0.3525	0.7297

Framework versions

Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Downloads last month: 4

Safetensors

Model size

0.3B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

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

Model tree for lbin2021/my-lecture-ocr

Unable to build the model tree, the base model loops to the model itself. Learn more.