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

Libraries

How to use AgenticFinLab/PyFi-QwenVL-3B-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-47K")

Transformers

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

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

pipe = pipeline("text-generation", model="AgenticFinLab/PyFi-QwenVL-3B-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-47K", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AgenticFinLab/PyFi-QwenVL-3B-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-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-47K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use AgenticFinLab/PyFi-QwenVL-3B-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-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-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-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-47K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

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

nielsr HF Staff

Update model card with metadata, paper link and training details

f823e45 verified about 2 months ago

2.79 kB

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

PyFi-QwenVL-3B-47K

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

Paper: PyFi: Toward Pyramid-like Financial Image Understanding for VLMs via Adversarial Agents
Repository: https://github.com/AgenticFinLab/PyFi
Dataset: PyFi-600K

Model Description

PyFi (Pyramid-like Financial Image Understanding) is a framework designed to enable Vision Language Models (VLMs) to reason through financial images—such as stock charts, financial reports, and economic diagrams—in a progressive, simple-to-complex manner.

This specific checkpoint is the 3B variant fine-tuned on approximately 47,000 reasoning chains. This version was trained without Chain-of-Thought (CoT), focusing on the model's ability to provide the final answer in the financial reasoning pyramid.

The model is designed to handle tasks across six hierarchical capability levels:

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

Training Details

Finetuning approach: LoRA (Parameter-Efficient Fine-Tuning) with full-module adaptation.
Training Data: 47K sample chains from the PyFi-600K dataset.
Optimizer: AdamW
Learning Rate: $1.0 \times 10^{-4}$
Learning Rate Schedule: Cosine scheduling with a warmup ratio of 0.1.
Training Epochs: 1
Effective Batch Size: 8
Hardware: 4x NVIDIA RTX 5090 GPUs.

Evaluation Results

In the PyFi benchmark, fine-tuning on pyramid-structured question chains showed significant improvements. The PyFi models (when using CoT) yielded average accuracy improvements of 19.52% for the 3B variant over baseline pre-trained models.

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}
}