first

app.py

@@ -1,11 +1,8 @@
 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")
+from transformers import pipeline
 
+# Load the model
+pipe = pipeline("text-generation", model="KoboldAI/fairseq-dense-13B-Shinen")
 
 def respond(
     message,
@@ -15,39 +12,32 @@ def respond(
     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,
+    # Construct the prompt from history and current message
+    prompt = system_message + "\n\n"
+    for user_msg, bot_msg in history:
+        prompt += f"Human: {user_msg}\nAI: {bot_msg}\n"
+    prompt += f"Human: {message}\nAI:"
+
+    # Generate response
+    response = pipe(
+        prompt,
+        max_length=len(prompt.split()) + max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        do_sample=True,
+    )[0]['generated_text']
 
-        response += token
-        yield response
+    # Extract only the AI's response
+    ai_response = response.split("AI:")[-1].strip()
+    
+    return ai_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=1, maximum=512, value=256, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
@@ -58,6 +48,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()