opendatalab / ChartVerse-4B

ChartVerse-4B is an efficient Vision Language Model (VLM) specialized for complex chart reasoning, developed as part of the opendatalab/ChartVerse project. For more details about our method, datasets, and full model series, please visit our Project Page .

A key highlight is that ChartVerse-4B significantly outperforms Qwen3-VL-8B-Thinking (60.0%) despite using only half the parameters , demonstrating that data quality triumphs over model scale.

🔥 Highlights

• Data Quality > Model Scale : 4B parameters achieving 61.9% average score, surpassing Qwen3-VL-8B-Thinking (60.0%)
• Efficient Performance : Delivers 8B-level performance with 4B parameters
• High-Quality Training : Trained on ChartVerse-SFT-600K and ChartVerse-RL-40K with rigorous truth-anchored QA synthesis
• Strong Reasoning : Equipped with Chain-of-Thought reasoning for complex multi-step chart analysis

📊 Model Performance

Overall Results

SFT vs RL Performance

📚 Training Data

ChartVerse-SFT-600K

• 412K unique high-complexity charts
• 603K QA pairs with 3.9B tokens of CoT reasoning
• Rollout Posterior Entropy: 0.44 (highest among all datasets)
• Truth-anchored answer verification via code execution

ChartVerse-RL-40K

• 40K highest-difficulty samples
• Filtered by failure rate: 0 < r(Q) < 1
• Ensures "hard but solvable" training signal

🏋️ Training Details

Supervised Fine-Tuning (SFT) :

• Framework: LLaMA-Factory
• Dataset: ChartVerse-SFT-600K
• Learning rate: 1.0 × 10⁻⁵
• Global batch size: 128
• Context length: 22,000 tokens

Reinforcement Learning (RL) :

• Framework: veRL
• Dataset: ChartVerse-RL-40K
• Algorithm: GSPO
• Learning rate: 1.0 × 10⁻⁶
• Rollout samples: 16 per prompt

🚀 Quick Start

from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
from PIL import Image

# 1. Load Model
model_path = "opendatalab/ChartVerse-4B"
model = Qwen3VLForConditionalGeneration.from_pretrained(
    model_path, torch_dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained(model_path)

# 2. Prepare Input
image_path = "path/to/your/chart.png"
query = "Which region demonstrates the greatest proportional variation in annual revenue compared to its typical revenue level?"

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image_path},
            {"type": "text", "text": query},
        ],
    }
]

# 3. Inference
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    padding=True,
    return_tensors="pt",
).to("cuda")
generated_ids = model.generate(**inputs, max_new_tokens=16384)
output_text = processor.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text[0])

📖 Citation

@article{chartverse2026,
  title={ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch},
  author={Anonymous Authors},
  journal={Anonymous ACL Submission},
  year={2026}
}

📄 License

This model is released under the Apache 2.0 License.

🙏 Acknowledgements

• Base model: Qwen3-VL-4B-Instruct
• Training frameworks: LLaMA-Factory , veRL
• Evaluation: VLMEvalKit