Instructions to use tencent/Hy-Embodied-VLM-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/Hy-Embodied-VLM-1.0 with Transformers:

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

pipe = pipeline("image-text-to-text", model="tencent/Hy-Embodied-VLM-1.0", 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 AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("tencent/Hy-Embodied-VLM-1.0", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tencent/Hy-Embodied-VLM-1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/Hy-Embodied-VLM-1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/Hy-Embodied-VLM-1.0",
		"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/tencent/Hy-Embodied-VLM-1.0

SGLang

How to use tencent/Hy-Embodied-VLM-1.0 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 "tencent/Hy-Embodied-VLM-1.0" \
    --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": "tencent/Hy-Embodied-VLM-1.0",
		"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 "tencent/Hy-Embodied-VLM-1.0" \
        --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": "tencent/Hy-Embodied-VLM-1.0",
		"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 tencent/Hy-Embodied-VLM-1.0 with Docker Model Runner:
```
docker model run hf.co/tencent/Hy-Embodied-VLM-1.0
```

Hy-Embodied-VLM-1.0 / config.json

Lavender11

init Hy-Embodied-VLM-1.0

aa947fc 5 days ago

Raw

History Blame Contribute Delete

2.69 kB

	{
	"architectures": [
	"HYV3VLForConditionalGeneration"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attention_head_dim": 128,
	"bos_token_id": 120000,
	"eod_token_id": 120020,
	"eos_token_id": 120025,
	"expert_hidden_dim": 768,
	"first_k_dense_replace": 1,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"image_start_token_id": 120118,
	"image_end_token_id": 120119,
	"image_token_id": 120120,
	"image_newline_token_id": 120121,
	"video_token_id": 120683,
	"video_start_token_id": 120122,
	"video_end_token_id": 120123,
	"initializer_range": 0.006,
	"intermediate_size": 6912,
	"max_position_embeddings": 32768,
	"mlp_bias": false,
	"model_type": "hy_v3_vl",
	"moe_router_enable_expert_bias": true,
	"moe_router_use_sigmoid": true,
	"n_group": null,
	"norm_topk_prob": true,
	"num_attention_heads": 32,
	"num_experts": 128,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 48,
	"num_key_value_heads": 4,
	"num_shared_experts": 1,
	"org_vocab_size": 120818,
	"pad_id": 120002,
	"pad_token_id": 120002,
	"qk_norm": true,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"rope_type": "default",
	"mrope_interleaved": true,
	"mrope_section": [
	24,
	20,
	20
	]
	},
	"rope_theta": 11158840,
	"route_norm": true,
	"router_scaling_factor": 2.826,
	"tie_word_embeddings": false,
	"transformers_version": "4.57.0",
	"use_cache": true,
	"use_grouped_mm": false,
	"vision_config": {
	"add_patchemb_bias": true,
	"attention_dropout": 0.0,
	"cat_extra_token": 0,
	"hidden_act": "gelu",
	"hidden_dropout": 0.0,
	"hidden_size": 1152,
	"img_max_token_num": 4096,
	"intermediate_size": 4304,
	"interpolate_mode": "bilinear",
	"max_image_size": 2048,
	"max_vit_seq_len": 16384,
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 27,
	"out_hidden_size": 2048,
	"patch_size": 16,
	"rms_norm_eps": 1e-05,
	"temporal_patch_size": 1,
	"spatial_patch_size": 1,
	"spatial_merge_size": 2,
	"perceive_post_norm": false,
	"video_spatial_compression": false,
	"video_temporal_compression": false
	},
	"vocab_size": 120818,
	"auto_map": {
	"AutoConfig": "configuration_hy_v3_vl.HYV3VLConfig",
	"AutoModel": "modeling_hy_v3_vl.HYV3VLModel",
	"AutoModelForCausalLM": "modeling_hy_v3_vl.HYV3VLForCausalLM",
	"AutoModelForImageTextToText": "modeling_hy_v3_vl.HYV3VLForConditionalGeneration",
	"AutoImageProcessor": "image_processing_hunyuan_vl.HunYuanVLImageProcessor",
	"AutoProcessor": "processing_hy_v3_vl.HYV3VLProcessor",
	"AutoVideoProcessor": "video_processing_hy_v3_vl.HYV3VLVideoProcessor"
	}
	}