Instructions to use AgenticFinLab/PyFi-QwenVL-7B-47K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AgenticFinLab/PyFi-QwenVL-7B-47K with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/home/yuxuanzhao/LLaMA-Factory/models/qwen2_5-vl-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "AgenticFinLab/PyFi-QwenVL-7B-47K")

Transformers

How to use AgenticFinLab/PyFi-QwenVL-7B-47K with Transformers:

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

pipe = pipeline("text-generation", model="AgenticFinLab/PyFi-QwenVL-7B-47K")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AgenticFinLab/PyFi-QwenVL-7B-47K", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AgenticFinLab/PyFi-QwenVL-7B-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-7B-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-7B-47K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AgenticFinLab/PyFi-QwenVL-7B-47K

SGLang

How to use AgenticFinLab/PyFi-QwenVL-7B-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-7B-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-7B-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-7B-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-7B-47K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AgenticFinLab/PyFi-QwenVL-7B-47K with Docker Model Runner:
```
docker model run hf.co/AgenticFinLab/PyFi-QwenVL-7B-47K
```

Improve model card and link to paper

by nielsr HF Staff - opened Apr 9

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+62

-174

Files changed (1) hide show

README.md +62 -174

README.md CHANGED Viewed

@@ -1,208 +1,96 @@
 ---
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
 library_name: peft
-pipeline_tag: text-generation
 tags:
 - base_model:adapter:Qwen/Qwen2.5-VL-7B-Instruct
 - llama-factory
 - lora
 - transformers
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
 ## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]
-### Framework versions
-- PEFT 0.17.1

 ---
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
 library_name: peft
+pipeline_tag: image-text-to-text
+license: apache-2.0
 tags:
 - base_model:adapter:Qwen/Qwen2.5-VL-7B-Instruct
 - llama-factory
 - lora
 - transformers
+- finance
+- financial-vlm
 ---
+# PyFi-QwenVL-7B-47K
+This repository contains a LoRA adapter for [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) fine-tuned using the **PyFi** framework for advanced financial image understanding.
 ## Model Details
+- **Developed by:** AgenticFin Lab
+- **Model type:** Vision-Language Model (VLM) LoRA Adapter
+- **Base model:** [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)
+- **Finetuning variant:** Trained on ~47K sample chains **without** Chain-of-Thought (CoT)
+- **License:** Apache 2.0
+- **Paper:** [PyFi: Toward Pyramid-like Financial Image Understanding for VLMs via Adversarial Agents](https://huggingface.co/papers/2512.14735)
+- **Repository:** [https://github.com/AgenticFinLab/PyFi](https://github.com/AgenticFinLab/PyFi)
+## Description
+**PyFi** (Pyramid-like Financial Image Understanding) is a framework designed to enhance VLMs in understanding complex financial images through adversarial agents. The framework uses **PyFi-600K**, a dataset organized into a reasoning pyramid across 6 capability levels:
+1. **Perception**: Basic visual understanding.
+2. **Data Extraction**: Foundational information retrieval.
+3. **Calculation Analysis**: Numerical analysis tasks.
+4. **Pattern Recognition**: Identifying trends and patterns.
+5. **Logical Reasoning**: Complex logical analysis.
+6. **Decision Support**: Strategic decision-making assistance.
+This specific model variant is fine-tuned on the final question-answer pairs of the reasoning chains, rather than the intermediate steps.
+## Usage Examples
+Below are examples of how to use the PyFi framework for financial analysis, as provided in the official repository.
+### MCTS Tree Construction for Financial Analysis
+```python
+from fttracer.mcts.gqa import ImageQASystem
+# Initialize the Image QA system
+system = ImageQASystem()
+# Analyze a financial report image with MCTS tree
+report_path = "examples/financial_report.png"
+# Run MCTS tree construction for comprehensive analysis
+system.main(
+    image_path=report_path,
+    context_base_path="examples/context/"
+)
+```
+### Endgame QA Generation for Financial Images
+```python
+from fttracer.mcts.gqa import ImageQASystem
+# Initialize the Image QA system
+system = ImageQASystem()
+# Analyze a stock chart and generate endgame QA
+stock_chart_path = "examples/stock_chart.png"
+# Generate endgame QA focused on final analysis
+system.main_gfa(
+    image_path=stock_chart_path,
+    context_base_path="examples/context/"
+)
+```
+## Evaluation Results
+Fine-tuning Qwen2.5-VL models on the pyramid-structured question chains enables these models to answer complex financial questions more effectively. According to the paper, the PyFi models show significant accuracy improvements, especially in high-level reasoning and decision support tasks compared to their base models.
+## Citation
+If you use PyFi in your research, please cite the following paper:
+```bibtex
+@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}
+}
+```