Spaces:
				
			
			
	
			
			
					
		Running
		
	
	
	
			
			
	
	
	
	
		
		
					
		Running
		
	
		edbeeching
		
	commited on
		
		
					Commit 
							
							·
						
						e621b4d
	
1
								Parent(s):
							
							0cb3106
								
add png with LFS support
Browse files- .gitattributes +2 -0
- app.py +5 -8
    	
        .gitattributes
    CHANGED
    
    | @@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text | |
| 33 | 
             
            *.zip filter=lfs diff=lfs merge=lfs -text
         | 
| 34 | 
             
            *.zst filter=lfs diff=lfs merge=lfs -text
         | 
| 35 | 
             
            *tfevents* filter=lfs diff=lfs merge=lfs -text
         | 
|  | |
|  | 
|  | |
| 33 | 
             
            *.zip filter=lfs diff=lfs merge=lfs -text
         | 
| 34 | 
             
            *.zst filter=lfs diff=lfs merge=lfs -text
         | 
| 35 | 
             
            *tfevents* filter=lfs diff=lfs merge=lfs -text
         | 
| 36 | 
            +
            *.png filter=lfs diff=lfs merge=lfs -text
         | 
| 37 | 
            +
            dataforge.png filter=lfs diff=lfs merge=lfs -text
         | 
    	
        app.py
    CHANGED
    
    | @@ -559,6 +559,8 @@ def main(): | |
| 559 |  | 
| 560 | 
             
                    DataForge is built on top of [DataTrove](https://github.com/huggingface/datatrove), our backend data generation script is open-source and available on [GitHub](https://github.com/huggingface/dataforge). DataForge is **FREE** for HuggingFace PRO users (10,000 samples) • 100 samples for free users.
         | 
| 561 | 
             
                    """)
         | 
|  | |
|  | |
| 562 |  | 
| 563 | 
             
                    # Usage guide and examples (right below description)
         | 
| 564 | 
             
                    with gr.Row():
         | 
| @@ -566,9 +568,9 @@ def main(): | |
| 566 | 
             
                            with gr.Accordion("Usage Guide", open=False):
         | 
| 567 | 
             
                                gr.Markdown("""
         | 
| 568 | 
             
                                **Step-by-Step Process:**
         | 
| 569 | 
            -
                                1. ** | 
| 570 | 
            -
                                2. **Load  | 
| 571 | 
            -
                                3. ** | 
| 572 | 
             
                                4. **Configure**: Set generation parameters
         | 
| 573 | 
             
                                5. **Submit**: Monitor progress in Statistics tab
         | 
| 574 |  | 
| @@ -583,10 +585,6 @@ def main(): | |
| 583 | 
             
                                gr.Markdown("""
         | 
| 584 | 
             
                                **Popular Use Cases:**
         | 
| 585 |  | 
| 586 | 
            -
                                **Educational**: Q&A datasets
         | 
| 587 | 
            -
                                - Models: Qwen3-4B, Phi-3.5-mini
         | 
| 588 | 
            -
                                - Temperature: 0.3-0.5
         | 
| 589 | 
            -
             | 
| 590 | 
             
                                **Conversational**: Multi-turn dialogues
         | 
| 591 | 
             
                                - Models: Llama-3.2-3B, Mistral-7B
         | 
| 592 | 
             
                                - Temperature: 0.7-0.9
         | 
| @@ -659,7 +657,6 @@ def main(): | |
| 659 | 
             
                                                    num_output_samples = gr.Slider(label="Number of samples, leave as '0' for all", value=0, minimum=0, maximum=MAX_SAMPLES_FREE, step=1, interactive=False, info="Click Load Info to populate")
         | 
| 660 |  | 
| 661 |  | 
| 662 | 
            -
                                gr.Markdown("**All generated datasets will be publicly available under the [synthetic-data-universe](https://huggingface.co/synthetic-data-universe) organization.**")
         | 
| 663 | 
             
                                submit_btn = gr.Button("Submit Generation Request", variant="primary")
         | 
| 664 | 
             
                                output_status = gr.Textbox(label="Status", interactive=False)
         | 
| 665 |  | 
|  | |
| 559 |  | 
| 560 | 
             
                    DataForge is built on top of [DataTrove](https://github.com/huggingface/datatrove), our backend data generation script is open-source and available on [GitHub](https://github.com/huggingface/dataforge). DataForge is **FREE** for HuggingFace PRO users (10,000 samples) • 100 samples for free users.
         | 
| 561 | 
             
                    """)
         | 
| 562 | 
            +
                    gr.Markdown("**All generated datasets will be publicly available under the [synthetic-data-universe](https://huggingface.co/synthetic-data-universe) organization.**")
         | 
| 563 | 
            +
                    
         | 
| 564 |  | 
| 565 | 
             
                    # Usage guide and examples (right below description)
         | 
| 566 | 
             
                    with gr.Row():
         | 
|  | |
| 568 | 
             
                            with gr.Accordion("Usage Guide", open=False):
         | 
| 569 | 
             
                                gr.Markdown("""
         | 
| 570 | 
             
                                **Step-by-Step Process:**
         | 
| 571 | 
            +
                                1. **Choose Model**: Select from 20+ models
         | 
| 572 | 
            +
                                2. **Load Dataset**: Enter a HF dataset name
         | 
| 573 | 
            +
                                3. **Load Info**: Click "Load Dataset Info"
         | 
| 574 | 
             
                                4. **Configure**: Set generation parameters
         | 
| 575 | 
             
                                5. **Submit**: Monitor progress in Statistics tab
         | 
| 576 |  | 
|  | |
| 585 | 
             
                                gr.Markdown("""
         | 
| 586 | 
             
                                **Popular Use Cases:**
         | 
| 587 |  | 
|  | |
|  | |
|  | |
|  | |
| 588 | 
             
                                **Conversational**: Multi-turn dialogues
         | 
| 589 | 
             
                                - Models: Llama-3.2-3B, Mistral-7B
         | 
| 590 | 
             
                                - Temperature: 0.7-0.9
         | 
|  | |
| 657 | 
             
                                                    num_output_samples = gr.Slider(label="Number of samples, leave as '0' for all", value=0, minimum=0, maximum=MAX_SAMPLES_FREE, step=1, interactive=False, info="Click Load Info to populate")
         | 
| 658 |  | 
| 659 |  | 
|  | |
| 660 | 
             
                                submit_btn = gr.Button("Submit Generation Request", variant="primary")
         | 
| 661 | 
             
                                output_status = gr.Textbox(label="Status", interactive=False)
         | 
| 662 |  |