Update app.py

app.py

@@ -1,20 +1,31 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-#from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 #client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-client = InferenceClient("vennify/t5-base-grammar-correction")
+#client = InferenceClient("vennify/t5-base-grammar-correction")
 #gr.load("models/vennify/t5-base-grammar-correction").launch()
 
 # Load the model and tokenizer
-#model_name = "vennify/t5-base-grammar-correction"
-#model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
-#tokenizer = AutoTokenizer.from_pretrained(model_name)
-
+model_name = "vennify/t5-base-grammar-correction"
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
+def correct_text(text, max_length, num_beams, temperature, top_p):
+    inputs = tokenizer.encode(text, return_tensors="pt")
+    outputs = model.generate(
+        inputs,
+        max_length=max_length,
+        num_beams=num_beams,
+        temperature=temperature,
+        top_p=top_p,
+        early_stopping=True
+    )
+    corrected_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return corrected_text
 
 
 def respond(
@@ -22,32 +33,22 @@ def respond(
     history: list[tuple[str, str]],
     system_message,
     max_tokens,
+    num_beams,
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    #messages = [{"role": "system", "content": system_message}]
 
-    messages.append({"role": "user", "content": message})
+    #for val in history:
+    #    if val[0]:
+    #        messages.append({"role": "user", "content": val[0]})
+    #    if val[1]:
+    #        messages.append({"role": "assistant", "content": val[1]})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    #messages.append({"role": "user", "content": message})
 
-        response += token
-        yield response
+    response = correct_text(message, max_tokens, num_beams, temperature, top_p)
+    yield response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -56,9 +57,10 @@ demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1,  maximum=2048, value=512,  step=1,    label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7,  step=0.1,  label="Temperature"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
+        gr.Slider(minimum=1,   maximum=2048, value=512,  step=1,    label="Max new tokens"),
+        gr.Slider(minimum=1,   maximum=10,   value=5,    step=1,    label="Num Beams"),
+        gr.Slider(minimum=0.1, maximum=4.0,  value=0.7,  step=0.1,  label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0,  value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )