Today (September 17th, 2024), we introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models (e.g., Llama 3-V 405B and InternVL 2). Remarkably, NVLM 1.0 shows improved text-only performance over its LLM backbone after multimodal training.
In this repo, we are open-sourcing NVLM-1.0-D-72B (decoder-only architecture), the decoder-only model weights and code for the community.
Inference Code (HF)   Training Code (Coming soon)   Website   Paper
We train our model with legacy Megatron-LM and adapt the codebase to Huggingface for model hosting, reproducibility, and inference. We observe numerical differences between the Megatron and Huggingface codebases, which are within the expected range of variation. We provide the results from both the Huggingface codebase and the Megatron codebase for reproducibility and comparison with other models.
Results (as of September 17th, 2024) in the multimodal benchmarks are as follows:
| Benchmark | MMMU (val / test) | MathVista | OCRBench | AI2D | ChartQA | DocVQA | TextVQA | RealWorldQA | VQAv2 |
|---|---|---|---|---|---|---|---|---|---|
| NVLM-D 1.0 72B (Huggingface) | 58.7 / 54.9 | 65.2 | 852 | 94.2 | 86.0 | 92.6 | 82.6 | 69.5 | 85.4 |
| NVLM-D 1.0 72B (Megatron) | 59.7 / 54.6 | 65.2 | 853 | 94.2 | 86.0 | 92.6 | 82.1 | 69.7 | 85.4 |
| Llama 3.2 90B | 60.3 / - | 57.3 | - | 92.3 | 85.5 | 90.1 | - | - | 78.1 |
| Llama 3-V 70B | 60.6 / - | - | - | 93.0 | 83.2 | 92.2 | 83.4 | - | 79.1 |
| Llama 3-V 405B | 64.5 / - | - | - | 94.1 | 85.8 | 92.6 | 84.8 | - | 80.2 |
| InternVL2-Llama3-76B | 55.2 / - | 65.5 | 839 | 94.8 | 88.4 | 94.1 | 84.4 | 72.2 | - |
| GPT-4V | 56.8 / 55.7 | 49.9 | 645 | 78.2 | 78.5 | 88.4 | 78.0 | 61.4 | 77.2 |
| GPT-4o | 69.1 / - | 63.8 | 736 | 94.2 | 85.7 | 92.8 | - | - | - |
| Claude 3.5 Sonnet | 68.3 / - | 67.7 | 788 | 94.7 | 90.8 | 95.2 | - | - | - |
| Gemini 1.5 Pro (Aug 2024) | 62.2 / - | 63.9 | 754 | 94.4 | 87.2 | 93.1 | 78.7 | 70.4 | 80.2 |
When converting Megatron checkpoint to Huggingface, we adapt InternVL codebase to support model loading and multi-GPU inference in HF. For training, please refer to Megatron-LM (Coming soon).
We provide a docker build file in the Dockerfile for reproduction.
The docker image is based on nvcr.io/nvidia/pytorch:23.09-py3.
Note: We observe that different transformer versions / CUDA versions / docker versions can lead to slight benchmark number differences. We recommend using the Dockerfile above for precise reproduction.
import torch
from transformers import AutoModel
path = "nvidia/NVLM-D-72B"
model = AutoModel.from_pretrained(
path,
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
use_flash_attn=False,
trust_remote_code=True).eval()
The model can be loaded on multiple GPUs as follows:
import torch
import math
from transformers import AutoModel
def split_model():
device_map = {}
world_size = torch.cuda.device_count()
num_layers = 80
# Since the first GPU will be used for ViT, treat it as half a GPU.
num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5))
num_layers_per_gpu = [num_layers_per_gpu] * world_size
num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5)
layer_cnt = 0
for i, num_layer in enumerate(num_layers_per_gpu):
for j in range(num_layer):
device_map[f'language_model.model.layers.{layer_cnt}'] = i
layer_cnt += 1
device_map['vision_model'] = 0
device_map['mlp1'] = 0
device_map['language_model.model.tok_embeddings'] = 0
device_map['language_model.model.embed_tokens'] = 0
device_map['language_model.output'] = 0
device_map['language_model.model.norm'] = 0
device_map['language_model.lm_head'] = 0
device_map[f'language_model.model.layers.{num_layers - 1}'] = 0
return device_map
path = "nvidia/NVLM-D-72B"
device_map = split_model()
model = AutoModel.from_pretrained(
path,
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
use_flash_attn=False,
trust_remote_code=True,
device_map=device_map).eval()
import torch
from transformers import AutoTokenizer, AutoModel
import math
from PIL import Image
import torchvision.transforms as T
from torchvision.transforms.functional import InterpolationMode
def split_model():
device_map = {}
world_size = torch.cuda.device_count()
num_layers = 80
# Since the first GPU will be used for ViT, treat it as half a GPU.
num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5))
num_layers_per_gpu = [num_layers_per_gpu] * world_size
num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5)
layer_cnt = 0
for i, num_layer in enumerate(num_layers_per_gpu):
for j in range(num_layer):
device_map[f'language_model.model.layers.{layer_cnt}'] = i
layer_cnt += 1
device_map['vision_model'] = 0
device_map['mlp1'] = 0
device_map['language_model.model.tok_embeddings'] = 0
device_map['language_model.model.embed_tokens'] = 0
device_map['language_model.output'] = 0
device_map['language_model.model.norm'] = 0
device_map['language_model.lm_head'] = 0
device_map[f'language_model.model.layers.{num_layers - 1}'] = 0
return device_map
IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)
def build_transform(input_size):
MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
transform = T.Compose([
T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
T.ToTensor(),
T.Normalize(mean=MEAN, std=STD)
])
return transform
def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
best_ratio_diff = float('inf')
best_ratio = (1, 1)
area = width * height
for ratio in target_ratios:
target_aspect_ratio = ratio[0] / ratio[1]
ratio_diff = abs(aspect_ratio - target_aspect_ratio)
if ratio_diff < best_ratio_diff:
best_ratio_diff = ratio_diff
best_ratio = ratio
elif ratio_diff == best_ratio_diff:
if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
best_ratio = ratio
return best_ratio
def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
orig_width, orig_height = image.size
aspect_ratio = orig_width / orig_height
# calculate the existing image aspect ratio
target_ratios = set(
(i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
i * j <= max_num and i * j >= min_num)
target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
# find the closest aspect ratio to the target
target_aspect_ratio = find_closest_aspect_ratio(
aspect_ratio, target_ratios, orig_width, orig_height, image_size)
# calculate the target width and height
target_width = image_size * target_aspect_ratio[0]
target_height = image_size * target_aspect_ratio[1]
blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
# resize the image
resized_img = image.resize((target_width, target_height))
processed_images = []
for i in range(blocks):
box = (
(i % (target_width // image_size)) * image_size,
(i // (target_width // image_size)) * image_size,
((i % (target_width // image_size)) + 1) * image_size,
((i // (target_width // image_size)) + 1) * image_size
)
# split the image
split_img = resized_img.crop(box)
processed_images.append(split_img)
assert len(processed_images) == blocks
if use_thumbnail and len(processed_images) != 1:
thumbnail_img = image.resize((image_size, image_size))
processed_images.append(thumbnail_img)
return processed_images
def load_image(image_file, input_size=448, max_num=12):
image = Image.open(image_file).convert('RGB')
transform = build_transform(input_size=input_size)
images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
pixel_values = [transform(image) for image in images]
pixel_values = torch.stack(pixel_values)
return pixel_values
path = "nvidia/NVLM-D-72B"
device_map = split_model()
model = AutoModel.from_pretrained(
path,
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
use_flash_attn=False,
trust_remote_code=True,
device_map=device_map).eval()
print(model)
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
generation_config = dict(max_new_tokens=1024, do_sample=False)
# pure-text conversation
question = 'Hello, who are you?'
response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')
# single-image single-round conversation
pixel_values = load_image('path/to/your/example/image.jpg', max_num=6).to(
torch.bfloat16)
question = '<image>\nPlease describe the image shortly.'
response = model.chat(tokenizer, pixel_values, question, generation_config)
print(f'User: {question}\nAssistant: {response}')
Wenliang Dai* (wdai@nvidia.com), Nayeon Lee* (nayeonl@nvidia.com), Boxin Wang* (boxinw@nvidia.com), Zhuolin Yang* (zhuoliny@nvidia.com), Wei Ping* (wping@nvidia.com)
*Equal contribution
@article{nvlm2024,
title={NVLM: Open Frontier-Class Multimodal LLMs},
author={Dai, Wenliang and Lee, Nayeon and Wang, Boxin and Yang, Zhuolin and Liu, Zihan and Barker, Jon and Rintamaki, Tuomas and Shoeybi, Mohammad and Catanzaro, Bryan and Ping, Wei},
journal={arXiv preprint},
year={2024}}
The use of this model is governed by the cc-by-nc-4.0