Upload folder using huggingface_hub

README.md

@@ -27,19 +27,11 @@ base_model:
 
 ## Usage
 
-Dependencies:
-
-* `transformers`
-* `torchaudio`
-
-TODO：以下由Qwen2.5-Omni-3B依赖，引入路径未知，需要去除
-
-* `pillow`
-* `torchvision`
-
-### Inference
-
 ```python
+>>> !pip install "transformers[torch]" torchaudio
+>>> # To load audio files, you may need to install additional dependencies, e.g. ffmpeg:
+>>> # !apt-get install ffmpeg
+
 >>> from transformers import AutoModelForCausalLM, AutoProcessor
 >>> model = AutoModelForCausalLM.from_pretrained("zhoukz/MiDashengLM-HF-dev", trust_remote_code=True)
 >>> model.eval()
@@ -56,7 +48,7 @@ TODO：以下由Qwen2.5-Omni-3B依赖，引入路径未知，需要去除
 ...     output = processor.batch_decode(generation, skip_special_tokens=True)
 
 >>> print(output)
-["An engine is idling.'"]
+["An engine is idling."]
 ```
 
 ## Citation