Update app.py

app.py

@@ -1,17 +1,40 @@
+from huggingface_hub import InferenceClient
 import gradio as gr
-from transformers import pipeline
-
-def correct_text(text, temperature=1.0, top_p=0.9, top_k=50):
-    model_id = "grammarly/coedit-large"
-    pipe = pipeline("text2text-generation", model=model_id, 
-                    generation_kwargs={"temperature": temperature, "top_p": top_p, "top_k": top_k})
-    corrected = pipe(text)[0]['generated_text']
-    return corrected
-
-interface = gr.Interface(fn=correct_text,
-                         inputs=[gr.inputs.TextArea(label="Input Text"),
-                                 gr.inputs.Slider(minimum=0.1, maximum=1.0, default=1.0, label="Temperature"),
-                                 gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.9, label="Top_p"),
-                                 gr.inputs.Slider(minimum=0, maximum=100, default=50, label="Top_k")],
-                         outputs="text")
-interface.launch()
+
+client = InferenceClient("grammarly/coedit-large")
+
+def generate(prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
+    temperature = float(temperature)
+    if temperature < 1e-2: temperature = 1e-2
+    top_p = float(top_p)
+
+    generate_kwargs = dict(temperature=temperature, max_new_tokens=max_new_tokens, top_p=top_p, top_k=top_k)  # seed=42,)
+
+    formatted_prompt = "Fix grammatical errors in this sentence: " + prompt
+    print("\nPROMPT: \n\t" + formatted_prompt)
+
+    # Generate text from the HF inference
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+
+    for response in stream:
+        output += response.token.text
+        yield output
+    return output
+    
+
+
+additional_inputs=[
+    gr.Slider( label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs", ),
+    gr.Slider( label="Max new tokens", value=256, minimum=0, maximum=1048, step=64, interactive=True, info="The maximum numbers of new tokens", ),
+    gr.Slider( label="Top-p (nucleus sampling)", value=0.90, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens", ),
+    gr.Slider( label="Top-k", value=0.90, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more TOP-K", )
+]
+
+gr.ChatInterface(
+    fn=generate,
+    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
+    additional_inputs=additional_inputs,
+    title="My Grammarly Space",
+    concurrency_limit=20,
+).launch(show_api=False)