Instructions to use AXERA-TECH/SmolVLM2-500M-Video-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AXERA-TECH/SmolVLM2-500M-Video-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="AXERA-TECH/SmolVLM2-500M-Video-Instruct")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AXERA-TECH/SmolVLM2-500M-Video-Instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AXERA-TECH/SmolVLM2-500M-Video-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AXERA-TECH/SmolVLM2-500M-Video-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AXERA-TECH/SmolVLM2-500M-Video-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AXERA-TECH/SmolVLM2-500M-Video-Instruct

SGLang

How to use AXERA-TECH/SmolVLM2-500M-Video-Instruct 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 "AXERA-TECH/SmolVLM2-500M-Video-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AXERA-TECH/SmolVLM2-500M-Video-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "AXERA-TECH/SmolVLM2-500M-Video-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AXERA-TECH/SmolVLM2-500M-Video-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AXERA-TECH/SmolVLM2-500M-Video-Instruct with Docker Model Runner:
```
docker model run hf.co/AXERA-TECH/SmolVLM2-500M-Video-Instruct
```

SmolVLM2-500M-Video-Instruct / .gitattributes

wangli

update project

31c43e4 verified 5 months ago

Raw

History Blame Contribute Delete

8.7 kB

	*.7z filter=lfs diff=lfs merge=lfs -text
	*.arrow filter=lfs diff=lfs merge=lfs -text
	*.bin filter=lfs diff=lfs merge=lfs -text
	*.bz2 filter=lfs diff=lfs merge=lfs -text
	*.ckpt filter=lfs diff=lfs merge=lfs -text
	*.ftz filter=lfs diff=lfs merge=lfs -text
	*.gz filter=lfs diff=lfs merge=lfs -text
	*.h5 filter=lfs diff=lfs merge=lfs -text
	*.joblib filter=lfs diff=lfs merge=lfs -text
	.lfs. filter=lfs diff=lfs merge=lfs -text
	*.mlmodel filter=lfs diff=lfs merge=lfs -text
	*.model filter=lfs diff=lfs merge=lfs -text
	*.msgpack filter=lfs diff=lfs merge=lfs -text
	*.npy filter=lfs diff=lfs merge=lfs -text
	*.npz filter=lfs diff=lfs merge=lfs -text
	*.onnx filter=lfs diff=lfs merge=lfs -text
	*.ot filter=lfs diff=lfs merge=lfs -text
	*.parquet filter=lfs diff=lfs merge=lfs -text
	*.pb filter=lfs diff=lfs merge=lfs -text
	*.pickle filter=lfs diff=lfs merge=lfs -text
	*.pkl filter=lfs diff=lfs merge=lfs -text
	*.pt filter=lfs diff=lfs merge=lfs -text
	*.pth filter=lfs diff=lfs merge=lfs -text
	*.rar filter=lfs diff=lfs merge=lfs -text
	*.safetensors filter=lfs diff=lfs merge=lfs -text
	saved_model/*/ filter=lfs diff=lfs merge=lfs -text
	.tar. filter=lfs diff=lfs merge=lfs -text
	*.tar filter=lfs diff=lfs merge=lfs -text
	*.tflite filter=lfs diff=lfs merge=lfs -text
	*.tgz filter=lfs diff=lfs merge=lfs -text
	*.wasm filter=lfs diff=lfs merge=lfs -text
	*.xz filter=lfs diff=lfs merge=lfs -text
	*.zip filter=lfs diff=lfs merge=lfs -text
	*.zst filter=lfs diff=lfs merge=lfs -text
	tfevents filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l29_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/vision_model_1x3x512x512_NHwC_U8.axmodel filter=lfs diff=lfs merge=lfs -text
	video/frame_0000.jpg filter=lfs diff=lfs merge=lfs -text
	video/frame_0040.jpg filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l13_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l14_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l7_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l20_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l28_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l5_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_post.axmodel filter=lfs diff=lfs merge=lfs -text
	video/frame_0024.jpg filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l10_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l11_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l16_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l31_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l3_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l6_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l0_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l17_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l26_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l23_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l4_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l9_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/model.embed_tokens.weight.bfloat16.bin filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l15_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l19_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l22_together.axmodel filter=lfs diff=lfs merge=lfs -text
	video/frame_0032.jpg filter=lfs diff=lfs merge=lfs -text
	main_api_ax650 filter=lfs diff=lfs merge=lfs -text
	main_ax650 filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l24_together.axmodel filter=lfs diff=lfs merge=lfs -text
	video/frame_0008.jpg filter=lfs diff=lfs merge=lfs -text
	video/frame_0016.jpg filter=lfs diff=lfs merge=lfs -text
	axera_logo.png filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l18_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l21_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l2_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l27_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l30_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l8_together.axmodel filter=lfs diff=lfs merge=lfs -text
	video/frame_0048.jpg filter=lfs diff=lfs merge=lfs -text
	video/frame_0056.jpg filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l12_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l1_together.axmodel filter=lfs diff=lfs merge=lfs -text
	SmolVLM2-500M-Video-Instruct_Ax650-C128-P768-CTX1024/llama_p128_l25_together.axmodel filter=lfs diff=lfs merge=lfs -text
	image.png filter=lfs diff=lfs merge=lfs -text
	llama_p128_l0_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l10_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l11_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l12_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l13_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l14_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l15_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l16_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l17_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l18_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l19_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l1_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l20_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l21_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l22_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l23_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l24_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l25_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l26_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l27_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l28_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l29_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l2_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l30_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l31_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l3_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l4_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l5_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l6_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l7_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l8_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_p128_l9_together.axmodel filter=lfs diff=lfs merge=lfs -text
	llama_post.axmodel filter=lfs diff=lfs merge=lfs -text
	vision_model_1x3x512x512_NHwC_U8.axmodel filter=lfs diff=lfs merge=lfs -text