Instructions to use OpenGVLab/InternVL2-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL2-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-4B", 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/InternVL2-4B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL2-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-4B"
# 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/InternVL2-4B",
		"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/InternVL2-4B

SGLang

How to use OpenGVLab/InternVL2-4B 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/InternVL2-4B" \
    --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/InternVL2-4B",
		"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/InternVL2-4B" \
        --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/InternVL2-4B",
		"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/InternVL2-4B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2-4B
```

InternVL2-4B / config.json

czczup

fix compatibility issue for transformers 4.46+

2a90414 verified over 1 year ago

raw

history blame contribute delete

6.63 kB

	{
	"_commit_hash": null,
	"architectures": [
	"InternVLChatModel"
	],
	"auto_map": {
	"AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
	"AutoModel": "modeling_internvl_chat.InternVLChatModel",
	"AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
	},
	"downsample_ratio": 0.5,
	"dynamic_image_size": true,
	"force_image_size": 448,
	"llm_config": {
	"_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
	"add_cross_attention": false,
	"architectures": [
	"Phi3ForCausalLM"
	],
	"attn_implementation": "flash_attention_2",
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_phi3.Phi3Config",
	"AutoModel": "modeling_phi3.Phi3ForCausalLM",
	"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
	},
	"bad_words_ids": null,
	"begin_suppress_tokens": null,
	"bos_token_id": 1,
	"chunk_size_feed_forward": 0,
	"cross_attention_hidden_size": null,
	"decoder_start_token_id": null,
	"diversity_penalty": 0.0,
	"do_sample": false,
	"early_stopping": false,
	"embd_pdrop": 0.0,
	"encoder_no_repeat_ngram_size": 0,
	"eos_token_id": 32000,
	"exponential_decay_length_penalty": null,
	"finetuning_task": null,
	"forced_bos_token_id": null,
	"forced_eos_token_id": null,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"initializer_range": 0.02,
	"intermediate_size": 8192,
	"is_decoder": false,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"length_penalty": 1.0,
	"max_length": 20,
	"max_position_embeddings": 131072,
	"min_length": 0,
	"model_type": "phi3",
	"no_repeat_ngram_size": 0,
	"num_attention_heads": 32,
	"num_beam_groups": 1,
	"num_beams": 1,
	"num_hidden_layers": 32,
	"num_key_value_heads": 32,
	"num_return_sequences": 1,
	"original_max_position_embeddings": 4096,
	"output_attentions": false,
	"output_hidden_states": false,
	"output_scores": false,
	"pad_token_id": 32000,
	"prefix": null,
	"problem_type": null,
	"pruned_heads": {},
	"remove_invalid_values": false,
	"repetition_penalty": 1.0,
	"resid_pdrop": 0.0,
	"return_dict": true,
	"return_dict_in_generate": false,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"long_factor": [
	1.0299999713897705,
	1.0499999523162842,
	1.0499999523162842,
	1.0799999237060547,
	1.2299998998641968,
	1.2299998998641968,
	1.2999999523162842,
	1.4499999284744263,
	1.5999999046325684,
	1.6499998569488525,
	1.8999998569488525,
	2.859999895095825,
	3.68999981880188,
	5.419999599456787,
	5.489999771118164,
	5.489999771118164,
	9.09000015258789,
	11.579999923706055,
	15.65999984741211,
	15.769999504089355,
	15.789999961853027,
	18.360000610351562,
	21.989999771118164,
	23.079999923706055,
	30.009998321533203,
	32.35000228881836,
	32.590003967285156,
	35.56000518798828,
	39.95000457763672,
	53.840003967285156,
	56.20000457763672,
	57.95000457763672,
	59.29000473022461,
	59.77000427246094,
	59.920005798339844,
	61.190006256103516,
	61.96000671386719,
	62.50000762939453,
	63.3700065612793,
	63.48000717163086,
	63.48000717163086,
	63.66000747680664,
	63.850006103515625,
	64.08000946044922,
	64.760009765625,
	64.80001068115234,
	64.81001281738281,
	64.81001281738281
	],
	"short_factor": [
	1.05,
	1.05,
	1.05,
	1.1,
	1.1,
	1.1500000000000001,
	1.2000000000000002,
	1.2500000000000002,
	1.3000000000000003,
	1.3500000000000003,
	1.5000000000000004,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.0500000000000007,
	2.0500000000000007,
	2.0500000000000007,
	2.1000000000000005,
	2.1000000000000005,
	2.1000000000000005,
	2.1500000000000004,
	2.1500000000000004,
	2.3499999999999996,
	2.549999999999999,
	2.5999999999999988,
	2.5999999999999988,
	2.7499999999999982,
	2.849999999999998,
	2.849999999999998,
	2.9499999999999975
	],
	"type": "su"
	},
	"rope_theta": 10000.0,
	"sep_token_id": null,
	"sliding_window": 262144,
	"suppress_tokens": null,
	"task_specific_params": null,
	"temperature": 1.0,
	"tf_legacy_loss": false,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": false,
	"tokenizer_class": null,
	"top_k": 50,
	"top_p": 1.0,
	"torch_dtype": "bfloat16",
	"torchscript": false,
	"transformers_version": "4.37.2",
	"typical_p": 1.0,
	"use_bfloat16": true,
	"use_cache": true,
	"vocab_size": 32020
	},
	"max_dynamic_patch": 12,
	"min_dynamic_patch": 1,
	"model_type": "internvl_chat",
	"ps_version": "v2",
	"select_layer": -1,
	"template": "phi3-chat",
	"torch_dtype": "bfloat16",
	"use_backbone_lora": 0,
	"use_llm_lora": 0,
	"use_thumbnail": true,
	"vision_config": {
	"architectures": [
	"InternVisionModel"
	],
	"attention_dropout": 0.0,
	"drop_path_rate": 0.0,
	"dropout": 0.0,
	"hidden_act": "gelu",
	"hidden_size": 1024,
	"image_size": 448,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"layer_norm_eps": 1e-06,
	"model_type": "intern_vit_6b",
	"norm_type": "layer_norm",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 24,
	"output_attentions": false,
	"output_hidden_states": false,
	"patch_size": 14,
	"qk_normalization": false,
	"qkv_bias": true,
	"return_dict": true,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.37.2",
	"use_bfloat16": true,
	"use_flash_attn": true
	}
	}