Upload folder using huggingface_hub

.gitattributes

@@ -32,3 +32,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/animal.png filter=lfs diff=lfs merge=lfs -text
+examples/bell_ring.wav filter=lfs diff=lfs merge=lfs -text
+examples/caixukun.mp4 filter=lfs diff=lfs merge=lfs -text
+examples/flower.mp4 filter=lfs diff=lfs merge=lfs -text
+examples/food_menu.png filter=lfs diff=lfs merge=lfs -text

app.py

@@ -200,19 +200,35 @@ def gradio_worker(
     with gr.Blocks(css=CSS, theme=gr.themes.Base()) as demo:
         gr.Markdown("## OneLLM: One Framework to Align All Modalities with Language")
         with gr.Row(equal_height=True):
-            # with gr.Column(scale=1):
-            #     img_path = gr.Image(label='Image Input', type='filepath')
-            #     video_path = gr.Video(label='Video Input')
-            #     audio_path = gr.Audio(label='Audio Input', type='filepath', sources=['upload'])
-            # modality = gr.Radio(choices=['image', 'audio', 'video'], value='image', interactive=True, label='Input Modalities', visible=False)
             modality = gr.Textbox(value='image', visible=False)
             with gr.Column(scale=1):
                 with gr.Tab('Image') as img_tab:
                     img_path = gr.Image(label='Image Input', type='filepath')
+                    gr.Examples(
+                        examples=[
+                            ["examples/animal.png", "Why this image is funny?"],
+                            ["examples/food_menu.png", "Introduce me the poster."],
+                            ],
+                        inputs=[img_path, msg],
+                    )
                 with gr.Tab('Video') as video_tab:
                     video_path = gr.Video(label='Video Input')
+                    gr.Examples(
+                        examples=[
+                            ["examples/flower.mp4", "What process does this video record?"],
+                            ["examples/caixukun.mp4", "Describe the video in detail."],
+                            ],
+                        inputs=[video_path, msg],
+                    )
                 with gr.Tab('Audio') as audio_tab:
                     audio_path = gr.Audio(label='Audio Input', type='filepath', sources=['upload'])
+                    gr.Examples(
+                        examples=[
+                            ["examples/bell_ring.wav", "What can you hear in the audio?"],
+                            ["examples/bird_audio.wav", "Describe the audio."],
+                            ],
+                        inputs=[audio_path, msg],
+                    )
 
             with gr.Column(scale=2):
                 chatbot = gr.Chatbot(elem_id="chatbot")

examples/bell_ring.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415b5406175cafa874396f89811121fb306c17084db8ec20753ab5666b4fdcca
+size 3630044

examples/caixukun.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5762ad0ae954da8fbc33d524e90969b9fc56745f2ce513724e2ff40da3f1ac16
+size 14008046

examples/flower.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f27dd2ae6f1a5cb836030983c9b423e182e6bf7de3e2138c97bf698c6f29ba
+size 3139496