We are thrilled to release our latest Eagle2 series Vision-Language Model. Open-source Vision-Language Models (VLMs) have made significant strides in narrowing the gap with proprietary models. However, critical details about data strategies and implementation are often missing, limiting reproducibility and innovation. In this project, we focus on VLM post-training from a data-centric perspective, sharing insights into building effective data strategies from scratch. By combining these strategies with robust training recipes and model design, we introduce Eagle2, a family of performant VLMs. Our work aims to empower the open-source community to develop competitive VLMs with transparent processes.

In this repo, we are open-sourcing Eagle2-2B, a lightweight model that achieves remarkable efficiency and speed while maintaining solid performance.

Model Zoo

We provide the following models:

model name	LLM	Vision	Max Length	HF Link
Eagle2-1B	Qwen2.5-0.5B-Instruct	Siglip	16K	🤗 link
Eagle2-2B	Qwen2.5-1.5B-Instruct	Siglip	16K	🤗 link
Eagle2-9B	Qwen2.5-7B-Instruct	Siglip+ConvNext	16K	🤗 link

Benchmark Results

Benchmark	InternVL2-2B	InternVL2.5-2B	InternVL2-4B	Qwen2-VL-2B	Eagle2-2B
DocVQA_test	86.9	88.7	89.2	90.1	88.0
ChartQA_test	76.2	79.2	81.5	73.0	82.0
InfoVQA_test	58.9	60.9	67.0	65.5	65.8
TextVQA_val	73.4	74.3	74.4	79.7	79.1
OCRBench	784	804	788	809	818
MME_sum	1876.8	2138.2	2059.8	1872.0	2109.8
RealWorldQA	57.3	60.1	60.7	62.6	63.1
AI2D_test	74.1	74.9	74.7	78.9	79.3
MMMU_val	36.3	43.6	47.9	41.1	43.1
MMVet_GPT-4-Turbo	39.5	60.8	51.0	49.5	53.8
HallBench_avg	37.9	42.6	41.9	41.7	45.8
MathVista_testmini	46.3	51.3	58.6	43.0	54.7
MMstar	50.1	53.7	54.3	48.0	56.4

Quick Start

We provide a inference script to help you quickly start using the model. We support different input types:

pure text input
single image input
multiple image input
video input

Install the dependencies

bash

pip install transformers
pip install flash-attn

single image

python

from PIL import Image
import requests
from transformers import AutoProcessor, AutoModel
import torch
model = AutoModel.from_pretrained("nvidia/Eagle2-1B",trust_remote_code=True, torch_dtype=torch.bfloat16)
processor = AutoProcessor.from_pretrained("nvidia/Eagle2-1B", trust_remote_code=True, use_fast=True)
processor.tokenizer.padding_side = "left"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://www.ilankelman.org/stopsigns/australia.jpg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

text_list = [processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)]
image_inputs, video_inputs = processor.process_vision_info(messages)
inputs = processor(text = text_list, images=image_inputs, videos=video_inputs, return_tensors="pt", padding=True)
inputs = inputs.to("cuda")
model = model.to("cuda")
generated_ids = model.generate(**inputs, max_new_tokens=1024)
output_text = processor.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

stream generation

python

from PIL import Image
import requests
from transformers import AutoProcessor, AutoModel, AutoTokenizer
import torch

from transformers import TextIteratorStreamer
import threading


model = AutoModel.from_pretrained("nvidia/Eagle2-1B",trust_remote_code=True, attn_implementation='flash_attention_2', torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained("nvidia/Eagle2-1B", trust_remote_code=True, use_fast=True)
processor = AutoProcessor.from_pretrained("nvidia/Eagle2-1B", trust_remote_code=True, use_fast=True)
processor.tokenizer.padding_side = "left"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://www.ilankelman.org/stopsigns/australia.jpg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

text_list = [processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)]
image_inputs, video_inputs = processor.process_vision_info(messages)
inputs = processor(text = text_list, images=image_inputs, videos=video_inputs, return_tensors="pt", padding=True)
inputs = inputs.to("cuda")
model = model.to("cuda")

streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

generation_kwargs = dict(
    **inputs,
    streamer=streamer,
    max_new_tokens=1024,
    do_sample=True,
    top_p=0.95,
    temperature=0.8
)
thread = threading.Thread(target=model.generate, kwargs=generation_kwargs)
thread.start()


for new_text in streamer:
    print(new_text, end="", flush=True)

multiple-images

python

from PIL import Image
import requests
from transformers import AutoProcessor, AutoModel
import torch
model = AutoModel.from_pretrained("nvidia/Eagle2-1B",trust_remote_code=True, torch_dtype=torch.bfloat16)
processor = AutoProcessor.from_pretrained("nvidia/Eagle2-1B", trust_remote_code=True, use_fast=True)
processor.tokenizer.padding_side = "left"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://www.ilankelman.org/stopsigns/australia.jpg",
            },
            {
                "type": "image",
                "image": "https://www.nvidia.com/content/dam/en-zz/Solutions/about-nvidia/logo-and-brand/01-nvidia-logo-vert-500x200-2c50-d@2x.png",
            },
            {"type": "text", "text": "Describe these two images."},
        ],
    }
]

text_list = [processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)]
image_inputs, video_inputs = processor.process_vision_info(messages)
inputs = processor(text = text_list, images=image_inputs, videos=video_inputs, return_tensors="pt", padding=True)
inputs = inputs.to("cuda")
model = model.to("cuda")
generated_ids = model.generate(**inputs, max_new_tokens=1024)
output_text = processor.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

single video

python

from PIL import Image
import requests
from transformers import AutoProcessor, AutoModel
import torch
model = AutoModel.from_pretrained("nvidia/Eagle2-1B",trust_remote_code=True, torch_dtype=torch.bfloat16)
processor = AutoProcessor.from_pretrained("nvidia/Eagle2-1B", trust_remote_code=True, use_fast=True)
processor.tokenizer.padding_side = "left"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "video",
                "video": "../Eagle2-8B/space_woaudio.mp4",
            },
            {"type": "text", "text": "Describe this video."},
        ],
    }
]

text_list = [processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)]
image_inputs, video_inputs, video_kwargs = processor.process_vision_info(messages, return_video_kwargs=True)

inputs = processor(text = text_list, images=image_inputs, videos=video_inputs, return_tensors="pt", padding=True, videos_kwargs=video_kwargs)
inputs = inputs.to("cuda")
model = model.to("cuda")
generated_ids = model.generate(**inputs, max_new_tokens=1024)
output_text = processor.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

multieple videos

python

from PIL import Image
import requests
from transformers import AutoProcessor, AutoModel
import torch
model = AutoModel.from_pretrained("nvidia/Eagle2-1B",trust_remote_code=True, torch_dtype=torch.bfloat16)
processor = AutoProcessor.from_pretrained("nvidia/Eagle2-1B", trust_remote_code=True, use_fast=True)
processor.tokenizer.padding_side = "left"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "video",
                "video": "../Eagle2-8B/space_woaudio.mp4",
                "nframes": 10,
            },
            {
                "type": "video",
                "video": "../Eagle2-8B/video_ocr.mp4",
                "nframes": 10,
            },
            {"type": "text", "text": "Describe these two videos respectively."},
        ],
    }
]

text_list = [processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)]
image_inputs, video_inputs, video_kwargs = processor.process_vision_info(messages, return_video_kwargs=True)
inputs = processor(text = text_list, images=image_inputs, videos=video_inputs, return_tensors="pt", padding=True, videos_kwargs=video_kwargs)
inputs = inputs.to("cuda")
model = model.to("cuda")
generated_ids = model.generate(**inputs, max_new_tokens=1024)
output_text = processor.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

batch inference

python

from PIL import Image
import requests
from transformers import AutoProcessor, AutoModel
import torch
model = AutoModel.from_pretrained("nvidia/Eagle2-1B",trust_remote_code=True, torch_dtype=torch.bfloat16)
processor = AutoProcessor.from_pretrained("nvidia/Eagle2-1B", trust_remote_code=True, use_fast=True)
processor.tokenizer.padding_side = "left"

messages1 = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://www.ilankelman.org/stopsigns/australia.jpg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

messages2 = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://www.nvidia.com/content/dam/en-zz/Solutions/about-nvidia/logo-and-brand/01-nvidia-logo-vert-500x200-2c50-d@2x.png",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

text_list = [processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
) for messages in [messages1, messages2]]
image_inputs, video_inputs = processor.process_vision_info([messages1, messages2])
inputs = processor(text = text_list, images=image_inputs, videos=video_inputs, return_tensors="pt", padding=True)
inputs = inputs.to("cuda")
model = model.to("cuda")
generated_ids = model.generate(**inputs, max_new_tokens=1024)
output_text = processor.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

TODO

Support vLLM Inference
Provide AWQ Quantization Weights
Provide fine-tuning scripts

License/Terms of Use

The code is released under the Apache 2.0 license as found in the LICENSE file.
The pretrained model weights are released under the Creative Commons Attribution: Non-Commercial 4.0 International
The service is a research preview intended for non-commercial use only, and is subject to the following licenses and terms:
- Model License of Qwen2.5-1.5B-Instruct: Apache-2.0
- Model License of PaliGemma: Gemma license

Citation

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please report security vulnerabilities or NVIDIA AI Concerns here.

nvidia/Eagle2-2B

Eagle-2

News:

Introduction

Model Zoo

Benchmark Results

Quick Start

Install the dependencies

single image

stream generation

multiple-images

single video

multieple videos

batch inference

TODO

License/Terms of Use

Citation

Ethical Considerations

nvidia/
Eagle2-2B