Instructions to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/home/yuxuanzhao/LLaMA-Factory/models/qwen2_5-vl-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "AgenticFinLab/PyFi-QwenVL-3B-COT-47K")

Transformers

How to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K with Transformers:

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

pipe = pipeline("text-generation", model="AgenticFinLab/PyFi-QwenVL-3B-COT-47K")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AgenticFinLab/PyFi-QwenVL-3B-COT-47K", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AgenticFinLab/PyFi-QwenVL-3B-COT-47K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AgenticFinLab/PyFi-QwenVL-3B-COT-47K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AgenticFinLab/PyFi-QwenVL-3B-COT-47K

SGLang

How to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K 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 "AgenticFinLab/PyFi-QwenVL-3B-COT-47K" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AgenticFinLab/PyFi-QwenVL-3B-COT-47K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "AgenticFinLab/PyFi-QwenVL-3B-COT-47K" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AgenticFinLab/PyFi-QwenVL-3B-COT-47K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AgenticFinLab/PyFi-QwenVL-3B-COT-47K with Docker Model Runner:
```
docker model run hf.co/AgenticFinLab/PyFi-QwenVL-3B-COT-47K
```

PyFi-QwenVL-3B-COT-47K / README.md

nielsr HF Staff

Improve model card and metadata

0b524d2 verified about 2 months ago

2.91 kB

base_model: Qwen/Qwen2.5-VL-3B-Instruct
library_name: peft
pipeline_tag: image-text-to-text
license: apache-2.0
tags:
  - finance
  - lora
  - vision-language
  - qwen

PyFi-QwenVL-3B-47K

This model is a fine-tuned LoRA adapter for Qwen2.5-VL-3B-Instruct, specialized for financial image understanding. It was introduced as part of the PyFi framework.

Model Details

Developed by: Yuqun Zhang, Yuxuan Zhao, Sijia Chen (AgenticFinLab)
Model type: Vision-Language Model (LoRA Adapter)
Base Model: Qwen/Qwen2.5-VL-3B-Instruct
Language(s): English
License: Apache 2.0
Paper: PyFi: Toward Pyramid-like Financial Image Understanding for VLMs via Adversarial Agents
Repository: https://github.com/AgenticFinLab/PyFi

Summary

PyFi (Pyramid-like Financial Image Understanding) is a framework designed to enhance Visual Language Models (VLMs) in understanding complex financial images through adversarial agents. The framework enables VLMs to reason through question chains in a progressive, simple-to-complex manner across six hierarchical capability levels:

Perception: Basic visual understanding
Data Extraction: Foundational information retrieval
Calculation Analysis: Numerical analysis tasks
Pattern Recognition: Identifying trends and patterns
Logical Reasoning: Complex logical analysis
Decision Support: Strategic decision-making assistance

This specific checkpoint was fine-tuned on approximately 47,000 question-answer chains from the PyFi-600K dataset. In this version ("w/o CoT"), only the question and answer from the final sample in each chain were used during training to target the ultimate reasoning goal.

Training Details

The model was fine-tuned with the following configuration:

Optimizer: AdamW
Learning Rate: $1.0 \times 10^{-4}$
Learning Rate Schedule: Cosine scheduling with warmup ratio of 0.1
Training Epochs: 1
Batch Size: Effective batch size of 8
PEFT: LoRA with full-module adaptation
Hardware: 4x NVIDIA RTX 5090 GPUs

Citation

If you use PyFi in your research, please cite:

@article{pyfi2025,
  title={PyFi: Toward Pyramid-like Financial Image Understanding for VLMs via Adversarial Agents},
  author={Zhang, Yuqun and Zhao, Yuxuan and Chen, Sijia},
  journal={arXiv preprint arXiv:2512.14735},
  year={2025}
}

Contact

For questions or inquiries, please contact:

Email: Yuqun Zhang (research@yuqunzhang.com) or Yuxuan Zhao (yx.zhao129@gmail.com)
GitHub Issues: https://github.com/AgenticFinLab/PyFi/issues