Instructions to use hf-internal-testing/tiny-processor-xiaomi_lens0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-processor-xiaomi_lens0 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-processor-xiaomi_lens0")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("hf-internal-testing/tiny-processor-xiaomi_lens0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hf-internal-testing/tiny-processor-xiaomi_lens0 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-processor-xiaomi_lens0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/tiny-processor-xiaomi_lens0",
		"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/hf-internal-testing/tiny-processor-xiaomi_lens0

SGLang

How to use hf-internal-testing/tiny-processor-xiaomi_lens0 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-processor-xiaomi_lens0" \
    --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": "hf-internal-testing/tiny-processor-xiaomi_lens0",
		"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 "hf-internal-testing/tiny-processor-xiaomi_lens0" \
        --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": "hf-internal-testing/tiny-processor-xiaomi_lens0",
		"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 hf-internal-testing/tiny-processor-xiaomi_lens0 with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-processor-xiaomi_lens0
```

guarin HF Staff commited on 7 days ago

Commit

e2f2af6

verified ·

1 Parent(s): cc61e2e

Use tiny Qwen image and video sizes for fast processor tests

Browse files

Files changed (2) hide show

README.md +1 -2
processor_config.json +8 -8

README.md CHANGED Viewed

@@ -12,8 +12,7 @@ and the processor configuration, tokenizer settings, and chat template from
 [guarin/Xiaomi-Lens-0](https://huggingface.co/guarin/Xiaomi-Lens-0/tree/1fe02dea90bfaaaf1d1311dc187a4466fdb9a1b8).
 Xiaomi control tokens are added to the tiny vocabulary. Token IDs are local to this
-fixture and are not compatible with the full model weights. Image and video settings
-are unchanged from Xiaomi-Lens-0; only the vocabulary is tiny. No model weights are included.
 Requires a Transformers version supporting XiaomiLens0Processor.
 ```python

 [guarin/Xiaomi-Lens-0](https://huggingface.co/guarin/Xiaomi-Lens-0/tree/1fe02dea90bfaaaf1d1311dc187a4466fdb9a1b8).
 Xiaomi control tokens are added to the tiny vocabulary. Token IDs are local to this
+fixture and are not compatible with the full model weights. Image and video size limits (784–3136 pixels) and patch size (4) use the tiny Qwen fixture settings for fast unit tests. The image min_pixels/max_pixels aliases match those limits. Other processor settings, the chat template, and tokenizer settings come from Xiaomi-Lens-0. No model weights are included.
 Requires a Transformers version supporting XiaomiLens0Processor.
 ```python

processor_config.json CHANGED Viewed

@@ -15,15 +15,15 @@
       0.5,
       0.5
     ],
-    "max_pixels": 8388608,
     "merge_size": 2,
-    "min_pixels": 65536,
-    "patch_size": 16,
     "resample": 3,
     "rescale_factor": 0.00392156862745098,
     "size": {
-      "longest_edge": 8388608,
-      "shortest_edge": 65536
     },
     "temporal_patch_size": 2
   },
@@ -48,13 +48,13 @@
     "max_frames": 768,
     "merge_size": 2,
     "min_frames": 4,
-    "patch_size": 16,
     "resample": 3,
     "rescale_factor": 0.00392156862745098,
     "return_metadata": false,
     "size": {
-      "longest_edge": 25165824,
-      "shortest_edge": 4096
     },
     "temporal_patch_size": 2,
     "video_processor_type": "Qwen3VLVideoProcessor"

       0.5,
       0.5
     ],
+    "max_pixels": 3136,
     "merge_size": 2,
+    "min_pixels": 784,
+    "patch_size": 4,
     "resample": 3,
     "rescale_factor": 0.00392156862745098,
     "size": {
+      "longest_edge": 3136,
+      "shortest_edge": 784
     },
     "temporal_patch_size": 2
   },
     "max_frames": 768,
     "merge_size": 2,
     "min_frames": 4,
+    "patch_size": 4,
     "resample": 3,
     "rescale_factor": 0.00392156862745098,
     "return_metadata": false,
     "size": {
+      "longest_edge": 3136,
+      "shortest_edge": 784
     },
     "temporal_patch_size": 2,
     "video_processor_type": "Qwen3VLVideoProcessor"