Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from transformers import pipeline, AutoTokenizer | |
| # 1. Load the model/pipeline (runs once at startup) | |
| classifier = pipeline("sentiment-analysis") | |
| # 2. Define the function Gradio will call for pipeline | |
| def analyze(text): | |
| # The pipeline can take a single string or a list. | |
| # Here we wrap a single user input in a list to match your example. | |
| results = classifier([text]) | |
| # Pretty-print the result | |
| r = results[0] | |
| return f"Label: {r['label']}\nConfidence: {r['score']:.4f}" | |
| # Build the UI | |
| # demo = gr.Interface( | |
| # fn=analyze, # your pipeline wrapper | |
| # inputs=gr.Textbox(lines=2, placeholder="Enter text here..."), | |
| # outputs=gr.Textbox(label="Result"), | |
| # title="Sentiment Analysis", | |
| # description="Running `transformers.pipeline('sentiment-analysis')` behind the scenes.", | |
| # examples=[ | |
| # ["I've been waiting for a HuggingFace course my whole life."], | |
| # ["I hate this so much!"] | |
| # ] | |
| # ) | |
| # Load tokenizer once (outside the UI) | |
| checkpoint = "distilbert-base-uncased-finetuned-sst-2-english" | |
| tokenizer = AutoTokenizer.from_pretrained(checkpoint) | |
| def tokenize_input(raw_inputs): | |
| """Tokenize text and return displayable results.""" | |
| if not raw_inputs or not raw_inputs.strip(): | |
| return {}, "Please enter some text." | |
| inputs = tokenizer(raw_inputs, padding=True, truncation=True, return_tensors="pt") | |
| # Convert tensors to plain Python types so Gradio can display them | |
| result = { | |
| "input_ids": inputs["input_ids"].tolist(), | |
| "attention_mask": inputs["attention_mask"].tolist() | |
| } | |
| # Also get human-readable token strings | |
| tokens = tokenizer.convert_ids_to_tokens(result["input_ids"][0]) | |
| return result, str(tokens) | |
| # ── Build the tabbed UI ───────────────────────────────── | |
| with gr.Blocks(title="Lesson Steps Comparison") as demo: | |
| gr.Markdown("# 🤗 Transformers Lesson: Side-by-Side Comparison") | |
| # ── Tab 1 ── | |
| with gr.Tab("Step 1: Sentiment Analysis"): | |
| gr.Markdown("**`pipeline('sentiment-analysis')`**") | |
| with gr.Row(): | |
| with gr.Column(): | |
| inp1 = gr.Textbox( | |
| lines=3, | |
| label="Input", | |
| placeholder="I've been waiting for a HuggingFace course..." | |
| ) | |
| btn1 = gr.Button("Analyze", variant="primary") | |
| out1 = gr.Textbox(label="Sentiment Result") | |
| btn1.click(analyze, inputs=inp1, outputs=out1) | |
| gr.Examples( | |
| examples=[ | |
| "I've been waiting for a HuggingFace course my whole life.", | |
| "I hate this so much!" | |
| ], | |
| inputs=inp1 | |
| ) | |
| # ── Tab 2 ── | |
| with gr.Tab("Tokenize"): | |
| gr.Markdown("### DistilBERT Tokenizer") | |
| with gr.Row(): | |
| with gr.Column(): | |
| text_input = gr.Textbox(lines=3, label="Input", placeholder="I've been waiting for a HuggingFace course...") | |
| tokenize_btn = gr.Button("Tokenize", variant="primary") | |
| json_output = gr.JSON(label="Tokenized Tensor Data") | |
| tokens_output = gr.Textbox(label="Human-Readable Tokens", | |
| lines=6) | |
| # Wire button → function → outputs | |
| tokenize_btn.click( | |
| fn=tokenize_input, | |
| inputs=text_input, | |
| outputs=[json_output, tokens_output] | |
| ) | |
| # ── Tab 3 ── | |
| # with gr.Tab("Step 3: [Another Comparison]"): | |
| # gr.Markdown("*Another tab for easy comparison.*") | |
| # inp3 = gr.Textbox(lines=3, label="Input") | |
| # btn3 = gr.Button("Run Step 3") | |
| # out3 = gr.Textbox(label="Output") | |
| # btn3.click(run_step_3, inputs=inp3, outputs=out3) | |
| # 4. Launch | |
| if __name__ == "__main__": | |
| demo.launch() |