Instructions to use trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6 with Transformers:

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

pipe = pipeline("image-text-to-text", model="trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6")
model = AutoModelForImageTextToText.from_pretrained("trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6",
		"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/trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6

SGLang

How to use trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6 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 "trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6" \
    --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": "trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6",
		"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 "trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6" \
        --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": "trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6",
		"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 trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6 with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-Qwen3_5MoeForConditionalGeneration-3.6
```

qgallouedec HF Staff commited on 21 days ago

Commit

37faca6

verified ·

1 Parent(s): f0e3fc0

Upload processor

Browse files

Files changed (3) hide show

processor_config.json +4 -1
tokenizer.json +2 -2
tokenizer_config.json +1 -2

processor_config.json CHANGED Viewed

@@ -1,5 +1,6 @@
 {
   "image_processor": {
     "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,
@@ -9,7 +10,7 @@
       0.5,
       0.5
     ],
-    "image_processor_type": "Qwen2VLImageProcessor",
     "image_std": [
       0.5,
       0.5,
@@ -27,6 +28,8 @@
   },
   "processor_class": "Qwen3VLProcessor",
   "video_processor": {
     "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,

 {
   "image_processor": {
+    "data_format": "channels_first",
     "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,
       0.5,
       0.5
     ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
     "image_std": [
       0.5,
       0.5,
   },
   "processor_class": "Qwen3VLProcessor",
   "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
     "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325

 version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json CHANGED Viewed

@@ -10,7 +10,6 @@
   "errors": "replace",
   "image_token": "<|image_pad|>",
   "is_local": false,
-  "local_files_only": false,
   "model_max_length": 262144,
   "model_specific_special_tokens": {
     "audio_bos_token": "<|audio_start|>",
@@ -25,7 +24,7 @@
   "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
   "processor_class": "Qwen3VLProcessor",
   "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null,
   "video_token": "<|video_pad|>",
   "vision_bos_token": "<|vision_start|>",

   "errors": "replace",
   "image_token": "<|image_pad|>",
   "is_local": false,
   "model_max_length": 262144,
   "model_specific_special_tokens": {
     "audio_bos_token": "<|audio_start|>",
   "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
   "processor_class": "Qwen3VLProcessor",
   "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
   "unk_token": null,
   "video_token": "<|video_pad|>",
   "vision_bos_token": "<|vision_start|>",