Instructions to use PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k with Transformers:

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

pipe = pipeline("image-text-to-text", model="PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k

SGLang

How to use PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k 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 "PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k" \
    --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": "PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k" \
        --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": "PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k with Docker Model Runner:
```
docker model run hf.co/PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k
```

Model Card for Eagle-X2-Llama3-8B-ConsecutiveTableReadout-Mix-160k

This model follows the adapter-based VLM structure from LLaVA and Eagle. This model uses meta-llama/Meta-Llama-3-8B-Instruct as the base LLM and CLIP-448 (based on CLIP-336) and ConvNeXt as the visual encoders.

Training Details

We trained Eagle-X2-Llama3-8B on 240k examples of Mix+ supervision on Table Readout.

Citation

Paper: Generalizing from SIMPLE to HARD Visual Reasoning

@misc{park2025generalizingsimplehardvisual,
      title={Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?}, 
      author={Simon Park and Abhishek Panigrahi and Yun Cheng and Dingli Yu and Anirudh Goyal and Sanjeev Arora},
      year={2025},
      eprint={2501.02669},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2501.02669}, 
}