Instructions to use OpenGVLab/InternVL2-26B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL2-26B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-26B", 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/InternVL2-26B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL2-26B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-26B"
# 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/InternVL2-26B",
		"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/InternVL2-26B

SGLang

How to use OpenGVLab/InternVL2-26B 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/InternVL2-26B" \
    --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/InternVL2-26B",
		"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/InternVL2-26B" \
        --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/InternVL2-26B",
		"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/InternVL2-26B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2-26B
```

czczup commited on Aug 23, 2024

Commit

696d810

verified ·

1 Parent(s): 4a03a6f

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

README.md +4 -4
configuration_intern_vit.py +1 -1
modeling_internvl_chat.py +2 -1

README.md CHANGED Viewed

@@ -144,7 +144,7 @@ model = AutoModel.from_pretrained(
     path,
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
-    use_flash_attn=False,
     trust_remote_code=True).eval().cuda()
 ```
@@ -159,7 +159,7 @@ model = AutoModel.from_pretrained(
     torch_dtype=torch.bfloat16,
     load_in_8bit=True,
     low_cpu_mem_usage=True,
-    use_flash_attn=False,
     trust_remote_code=True).eval()
 ```
@@ -208,7 +208,7 @@ 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()
 ```
@@ -305,7 +305,7 @@ model = AutoModel.from_pretrained(
     path,
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
-    use_flash_attn=False,
     trust_remote_code=True).eval().cuda()
 tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)

     path,
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
+    use_flash_attn=True,
     trust_remote_code=True).eval().cuda()
 ```
     torch_dtype=torch.bfloat16,
     load_in_8bit=True,
     low_cpu_mem_usage=True,
+    use_flash_attn=True,
     trust_remote_code=True).eval()
 ```
     path,
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
+    use_flash_attn=True,
     trust_remote_code=True,
     device_map=device_map).eval()
 ```
     path,
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
+    use_flash_attn=True,
     trust_remote_code=True).eval().cuda()
 tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)

configuration_intern_vit.py CHANGED Viewed

@@ -71,7 +71,7 @@ class InternVisionConfig(PretrainedConfig):
             intermediate_size=12800,
             qk_normalization=True,
             num_hidden_layers=48,
-            use_flash_attn=False,
             hidden_act='gelu',
             norm_type='rms_norm',
             layer_norm_eps=1e-6,

             intermediate_size=12800,
             qk_normalization=True,
             num_hidden_layers=48,
+            use_flash_attn=True,
             hidden_act='gelu',
             norm_type='rms_norm',
             layer_norm_eps=1e-6,

modeling_internvl_chat.py CHANGED Viewed

@@ -18,7 +18,7 @@ from transformers.utils import ModelOutput, logging
 from .configuration_internvl_chat import InternVLChatConfig
 from .conversation import get_conv_template
-from .modeling_intern_vit import InternVisionModel
 from .modeling_internlm2 import InternLM2ForCausalLM
 logger = logging.get_logger(__name__)
@@ -50,6 +50,7 @@ class InternVLChatModel(PreTrainedModel):
         self.num_image_token = int((image_size // patch_size) ** 2 * (config.downsample_ratio ** 2))
         self.downsample_ratio = config.downsample_ratio
         self.ps_version = config.ps_version
         config.vision_config.use_flash_attn = True if use_flash_attn else False
         config.llm_config.attn_implementation = 'flash_attention_2' if use_flash_attn else 'eager'

 from .configuration_internvl_chat import InternVLChatConfig
 from .conversation import get_conv_template
+from .modeling_intern_vit import InternVisionModel, has_flash_attn
 from .modeling_internlm2 import InternLM2ForCausalLM
 logger = logging.get_logger(__name__)
         self.num_image_token = int((image_size // patch_size) ** 2 * (config.downsample_ratio ** 2))
         self.downsample_ratio = config.downsample_ratio
         self.ps_version = config.ps_version
+        use_flash_attn = use_flash_attn if has_flash_attn else False
         config.vision_config.use_flash_attn = True if use_flash_attn else False
         config.llm_config.attn_implementation = 'flash_attention_2' if use_flash_attn else 'eager'