Instructions to use chunhuizng/AudioOnlyThinker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chunhuizng/AudioOnlyThinker with Transformers:

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

pipe = pipeline("text-generation", model="chunhuizng/AudioOnlyThinker", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("chunhuizng/AudioOnlyThinker", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use chunhuizng/AudioOnlyThinker with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chunhuizng/AudioOnlyThinker"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chunhuizng/AudioOnlyThinker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chunhuizng/AudioOnlyThinker

SGLang

How to use chunhuizng/AudioOnlyThinker 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 "chunhuizng/AudioOnlyThinker" \
    --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": "chunhuizng/AudioOnlyThinker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "chunhuizng/AudioOnlyThinker" \
        --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": "chunhuizng/AudioOnlyThinker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use chunhuizng/AudioOnlyThinker with Docker Model Runner:
```
docker model run hf.co/chunhuizng/AudioOnlyThinker
```

chunhuizng commited on Apr 9, 2025

Commit

392ead7

verified ·

1 Parent(s): a0f47b4

Update README.md

Browse files

Files changed (1) hide show

README.md +21 -0

README.md CHANGED Viewed

@@ -49,6 +49,27 @@ class AudioOnlyThinker(Qwen2_5OmniThinkerForConditionalGeneration):
         return super().forward(*args, pixel_values=None, pixel_values_videos=None, **kwargs)
 model = AudioOnlyThinker.from_pretrained("chunhuizng/AudioOnlyThinker")
 ```
 ---

         return super().forward(*args, pixel_values=None, pixel_values_videos=None, **kwargs)
 model = AudioOnlyThinker.from_pretrained("chunhuizng/AudioOnlyThinker")
+from audio_only_processor import AudioOnlyProcessor
+processor = AudioOnlyProcessor.from_pretrained("chunhuizng/AudioOnlyThinker")
+conversation = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "audio", "path": "your_audio.wav"},
+            {"type": "text", "text": "What is being said in this audio?"}
+        ]
+    }
+]
+inputs = processor.apply_chat_template(conversation, tokenize=True, return_tensors="pt")
+inputs = {k: v.to(model.device) for k, v in inputs.items()}
+outputs = model.generate(**inputs, max_new_tokens=128)
+response = processor.batch_decode(outputs, skip_special_tokens=True)[0]
+print(response)
 ```
 ---