Instructions to use hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration with Transformers:

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

pipe = pipeline("image-text-to-text", model="hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration")
model = AutoModelForImageTextToText.from_pretrained("hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration

SGLang

How to use hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration 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 "hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration" \
    --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": "hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration",
		"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 "hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration" \
        --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": "hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-Qwen3VLMoeForConditionalGeneration
```

tiny-random-Qwen3VLMoeForConditionalGeneration / config.json

3outeille HF Staff

Upload Qwen3VLMoeForConditionalGeneration

238d529 verified 6 months ago

raw

history blame contribute delete

1.52 kB

	{
	"architectures": [
	"Qwen3VLMoeForConditionalGeneration"
	],
	"dtype": "float32",
	"image_token_id": 151655,
	"model_type": "qwen3_vl_moe",
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"decoder_sparse_step": 1,
	"head_dim": 16,
	"hidden_act": "silu",
	"hidden_size": 64,
	"initializer_range": 0.02,
	"intermediate_size": 128,
	"max_position_embeddings": 128000,
	"mlp_only_layers": [],
	"model_type": "qwen3_vl_moe_text",
	"moe_intermediate_size": 64,
	"num_attention_heads": 4,
	"num_experts": 4,
	"num_experts_per_tok": 2,
	"num_hidden_layers": 2,
	"num_key_value_heads": 2,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"rope_theta": 5000000.0,
	"rope_type": "default"
	},
	"use_cache": true,
	"vocab_size": 1000
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.0.0.dev0",
	"video_token_id": 151656,
	"vision_config": {
	"deepstack_visual_indexes": [
	8,
	16,
	24
	],
	"depth": 27,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 64,
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 128,
	"model_type": "qwen3_vl_moe",
	"num_attention_heads": 4,
	"num_heads": 16,
	"num_hidden_layers": 2,
	"num_position_embeddings": 2304,
	"out_hidden_size": 3584,
	"patch_size": 14,
	"spatial_merge_size": 2,
	"temporal_patch_size": 2
	},
	"vision_end_token_id": 151653,
	"vision_start_token_id": 151652
	}