Instructions to use YUNGHUI2024/deepseek-ocr2-chart-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YUNGHUI2024/deepseek-ocr2-chart-v1 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-OCR-2")
model = PeftModel.from_pretrained(base_model, "YUNGHUI2024/deepseek-ocr2-chart-v1")

Transformers

How to use YUNGHUI2024/deepseek-ocr2-chart-v1 with Transformers:

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

pipe = pipeline("text-generation", model="YUNGHUI2024/deepseek-ocr2-chart-v1")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("YUNGHUI2024/deepseek-ocr2-chart-v1", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YUNGHUI2024/deepseek-ocr2-chart-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YUNGHUI2024/deepseek-ocr2-chart-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YUNGHUI2024/deepseek-ocr2-chart-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/YUNGHUI2024/deepseek-ocr2-chart-v1

SGLang

How to use YUNGHUI2024/deepseek-ocr2-chart-v1 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 "YUNGHUI2024/deepseek-ocr2-chart-v1" \
    --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": "YUNGHUI2024/deepseek-ocr2-chart-v1",
		"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 "YUNGHUI2024/deepseek-ocr2-chart-v1" \
        --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": "YUNGHUI2024/deepseek-ocr2-chart-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use YUNGHUI2024/deepseek-ocr2-chart-v1 with Docker Model Runner:
```
docker model run hf.co/YUNGHUI2024/deepseek-ocr2-chart-v1
```

deepseek-ocr2-chart-v1

This model is a fine-tuned version of deepseek-ai/DeepSeek-OCR-2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6978

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: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
1.3769	0.5714	1	1.2913
1.3769	1.7143	3	0.9567
0.9714	2.8571	5	0.7840
0.9714	4.0	7	0.7222
0.9714	4.5714	8	0.7006
0.5974	5.7143	10	0.6978

Framework versions

PEFT 0.19.1
Transformers 4.46.3
Pytorch 2.6.0+cu124
Datasets 4.8.5
Tokenizers 0.20.3

Generated by ML Intern

This model repository was generated by ML Intern, an agent for machine learning research and development on the Hugging Face Hub.

Try ML Intern: https://smolagents-ml-intern.hf.space
Source code: https://github.com/huggingface/ml-intern

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = 'YUNGHUI2024/deepseek-ocr2-chart-v1'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

For non-causal architectures, replace AutoModelForCausalLM with the appropriate AutoModel class.

Downloads last month: 217

Model tree for YUNGHUI2024/deepseek-ocr2-chart-v1

Base model

deepseek-ai/DeepSeek-OCR-2

Adapter

(5)

this model