Instructions to use OpenGVLab/InternVL-Chat-V1-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL-Chat-V1-2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL-Chat-V1-2", trust_remote_code=True)
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 AutoModel
model = AutoModel.from_pretrained("OpenGVLab/InternVL-Chat-V1-2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL-Chat-V1-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL-Chat-V1-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL-Chat-V1-2",
		"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/OpenGVLab/InternVL-Chat-V1-2

SGLang

How to use OpenGVLab/InternVL-Chat-V1-2 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 "OpenGVLab/InternVL-Chat-V1-2" \
    --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": "OpenGVLab/InternVL-Chat-V1-2",
		"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 "OpenGVLab/InternVL-Chat-V1-2" \
        --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": "OpenGVLab/InternVL-Chat-V1-2",
		"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 OpenGVLab/InternVL-Chat-V1-2 with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL-Chat-V1-2
```

'return_dict'

by deryauysal - opened May 13, 2025

Discussion

deryauysal

May 13, 2025

I give an image and a prompt the model but I get this error: got multiple values for keyword argument 'return_dict'.
My code:

from transformers import AutoTokenizer, AutoModel, CLIPImageProcessor
from PIL import Image
import torch
import os
import math

#os.environ["CUDA_VISIBLE_DEVICES"] = "3"
def split_model(model_name):
device_map = {}
world_size = torch.cuda.device_count()
num_layers = {'InternVL-Chat-V1-2': 60, 'InternVL-Chat-V1-2-Plus': 60}[model_name]
# 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
print("num_layers_per_gpu",num_layers_per_gpu)
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'] = 3
device_map['mlp1'] = 3
device_map['language_model.model.tok_embeddings'] = 3
device_map['language_model.model.embed_tokens'] = 2
device_map['language_model.output'] = 3
device_map['language_model.model.norm'] = 3
device_map['language_model.model.rotary_emb'] = 3
device_map['language_model.lm_head'] = 3
device_map[f'language_model.model.layers.{num_layers - 1}'] = 3
print("device_map",device_map)
return device_map

path = "OpenGVLab/InternVL-Chat-V1-2"
device_map = split_model('InternVL-Chat-V1-2')
model = AutoModel.from_pretrained(
path,
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
use_flash_attn=True,
trust_remote_code=True,
device_map=device_map).eval()
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
image_processor = CLIPImageProcessor.from_pretrained(path)
image = Image.open('......jpg').resize((448, 448))

Görsel

pixel_values = image_processor(images=image, return_tensors='pt').pixel_values.to(torch.bfloat16)
generation_config = dict(max_new_tokens=1024, do_sample=True)

Modelin chat formatına göre input oluştur

question = '\nVerilen belge içerisinden şu bilgileri çıkar .....'
response = model.chat(tokenizer, pixel_values, question, generation_config)
print(f'User: {question}')
print(f'Assistant: {response}')

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment