Instructions to use OpenGVLab/InternVL2-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL2-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-2B", 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/InternVL2-2B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL2-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-2B"
# 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/InternVL2-2B",
		"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/InternVL2-2B

SGLang

How to use OpenGVLab/InternVL2-2B 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/InternVL2-2B" \
    --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/InternVL2-2B",
		"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/InternVL2-2B" \
        --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/InternVL2-2B",
		"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/InternVL2-2B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2-2B
```

czczup commited on Nov 21, 2024

Commit

54ef5b6

verified ·

1 Parent(s): faa8fea

Delete test_long_niah.sh

Browse files

Files changed (1) hide show

test_long_niah.sh +0 -77

test_long_niah.sh DELETED Viewed

@@ -1,77 +0,0 @@
-PARTITION=${PARTITION:-"Intern5"}
-GPUS=${GPUS:-16}
-GPUS_PER_NODE=${GPUS_PER_NODE:-8}
-GPUS_PER_TASK=${GPUS_PER_TASK:-1}
-QUOTA_TYPE=${QUOTA_TYPE:-"reserved"}
-set -x
-CHECKPOINT=${1}
-JOB_FOLDER=$(dirname "$CHECKPOINT")
-files=(
-    "$JOB_FOLDER/configuration_intern_vit.py"
-    "$JOB_FOLDER/configuration_internlm2.py"
-    "$JOB_FOLDER/configuration_internvl_chat.py"
-    "$JOB_FOLDER/conversation.py"
-    "$JOB_FOLDER/modeling_intern_vit.py"
-    "$JOB_FOLDER/modeling_internlm2.py"
-    "$JOB_FOLDER/modeling_internvl_chat.py"
-    "$JOB_FOLDER/tokenization_internlm2_fast.py"
-    "$JOB_FOLDER/tokenization_internlm2.py"
-    "test_long_niah.sh"
-)
-for file in "${files[@]}"; do
-    dest_file="$CHECKPOINT/$(basename "$file")"
-    if [ ! -f "$dest_file" ]; then
-        cp "$file" "$CHECKPOINT"
-    fi
-done
-ARGS=("$@")
-declare -a tasks=( \
-'retrieval-image-test-long-subset' \
-'retrieval-image-test-long-128k' \
-)
-# declare -a tasks=(\
-#     'retrieval-image-test-long-1M'\
-# )
-declare -a tasks=(\
-    'retrieval-image-test-long-800k' \
-    'retrieval-image-test-long-512k' \
-)
-model_name="internvl"
-for STRIDE in 1; do
-    LOG_DIR=$CHECKPOINT/eval_mm_niah_ring_attn_$STRIDE
-    mkdir -p $LOG_DIR
-    for ((j=0; j<${#tasks[@]}; j++)); do
-        task=${tasks[j]}
-        echo "$(date) ${model_name}_${task}_stride_${STRIDE}"
-        srun -p ${PARTITION} \
-                --gres=gpu:${GPUS_PER_NODE} \
-                --ntasks=$((GPUS / GPUS_PER_TASK)) \
-                --ntasks-per-node=$((GPUS_PER_NODE / GPUS_PER_TASK)) \
-                --quotatype=${QUOTA_TYPE} \
-                --job-name="${STRIDE}${task}" \
-                -o "${LOG_DIR}/${task}_stride_${STRIDE}.log" \
-                -e "${LOG_DIR}/${task}_stride_${STRIDE}.log" \
-                --async \
-                python -u eval/mm_niah/eval_mm_niah_long.py \
-                --checkpoint $CHECKPOINT \
-                --outputs-dir $LOG_DIR \
-                --task $task \
-                --num-gpus-per-rank ${GPUS_PER_TASK} "${ARGS[@]:1}" \
-                --rope_pos_id_version 'v5' \
-                --ring_attn \
-                --rope_pos_id_stride $STRIDE \
-        sleep 0.2
-    done
-done