new code

app.py

@@ -1,64 +1,61 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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("antony-pk/Phi-3-mini-4k-instruct-erpnext")
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
+# Load your model and tokenizer
+model_name = "antony-pk/Phi-3-mini-4k-instruct-erpnext"
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history,
     system_message,
     max_tokens,
     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.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Preparing the conversation history for the model
+    inputs = [{"role": "system", "content": system_message}]
+    
+    for user_input, bot_response in history:
+        if user_input:
+            inputs.append({"role": "user", "content": user_input})
+        if bot_response:
+            inputs.append({"role": "assistant", "content": bot_response})
+
+    inputs.append({"role": "user", "content": message})
+
+    # Encode the inputs
+    input_ids = tokenizer.encode(
+        tokenizer.convert_tokens_to_string(inputs), 
+        return_tensors="pt"
+    )
+    
+    # Generate the response
+    output = model.generate(
+        input_ids,
+        max_length=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-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)",
-        ),
+        num_return_sequences=1
+    )
+    
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
+
+# Define the Gradio interface
+interface = gr.Interface(
+    fn=respond,
+    inputs=[
+        gr.inputs.Textbox(label="Message"),
+        gr.inputs.Dataframe(headers=["User", "Assistant"], default=[]),
+        gr.inputs.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.inputs.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.inputs.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.inputs.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
+    outputs="text",
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    interface.launch()