Instructions to use cyttic/heb-verifier17-connected with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cyttic/heb-verifier17-connected with Transformers:

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

pipe = pipeline("image-text-to-text", model="cyttic/heb-verifier17-connected")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("cyttic/heb-verifier17-connected")
model = AutoModelForMultimodalLM.from_pretrained("cyttic/heb-verifier17-connected", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cyttic/heb-verifier17-connected with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cyttic/heb-verifier17-connected"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cyttic/heb-verifier17-connected",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cyttic/heb-verifier17-connected

SGLang

How to use cyttic/heb-verifier17-connected 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 "cyttic/heb-verifier17-connected" \
    --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": "cyttic/heb-verifier17-connected",
		"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 "cyttic/heb-verifier17-connected" \
        --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": "cyttic/heb-verifier17-connected",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cyttic/heb-verifier17-connected with Docker Model Runner:
```
docker model run hf.co/cyttic/heb-verifier17-connected
```

heb-verifier17-connected

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0546
Cer: 0.0209
Exact: 0.9619

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: 1e-05
train_batch_size: 16
eval_batch_size: 32
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: 0.05
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Exact
0.1357	0.3729	500	0.1282	0.0503	0.9104
0.1084	0.7457	1000	0.0856	0.0362	0.9384
0.0478	1.1186	1500	0.0732	0.0260	0.9518
0.0625	1.4914	2000	0.0542	0.0215	0.9630
0.0567	1.8643	2500	0.0567	0.0220	0.9597
0.0336	2.2371	3000	0.0473	0.0209	0.9619
0.0427	2.6100	3500	0.0334	0.0164	0.9720
0.0354	2.9828	4000	0.0370	0.0153	0.9709
0.0354	3.0	4023	0.0546	0.0209	0.9619

Framework versions

Transformers 5.13.1
Pytorch 2.11.0+cu128
Datasets 5.0.0
Tokenizers 0.22.2

Downloads last month: 52

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

cyttic
/

heb-verifier17-connected

heb-verifier17-connected

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Space using cyttic/heb-verifier17-connected 1