change model4

app.py

@@ -1,65 +1,58 @@
 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("cognitivecomputations/dolphin-2.9.4-llama3.1-8b-gguf")
-
-
-# def respond(
-#     message,
-#     history: list[tuple[str, str]],
-#     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,
-#         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)",
-#         ),
-#     ],
-# )
-
-
-# if __name__ == "__main__":
-#     demo.launch()
-gr.load("cognitivecomputations/dolphin-2.9.4-llama3.1-8b").launch()
+from transformers import pipeline
+
+# Initialize the pipeline for text generation
+pipe = pipeline("text-generation", model="meta-llama/Llama-3.1-8B")
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    # Prepare conversation history with system message
+    conversation_history = system_message + "\n"
+    for user_message, assistant_message in history:
+        if user_message:
+            conversation_history += f"User: {user_message}\n"
+        if assistant_message:
+            conversation_history += f"Assistant: {assistant_message}\n"
+    conversation_history += f"User: {message}\n"
+
+    # Generate response
+    response = ""
+    result = pipe(
+        conversation_history,
+        max_length=max_tokens,
+        do_sample=True,
+        temperature=temperature,
+        top_p=top_p
+    )[0]["generated_text"]
+
+    # Extract only the new assistant response
+    new_response = result.split(conversation_history)[-1].strip()
+    for token in new_response:
+        response += token
+        yield response
+
+# Define Gradio interface
+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)",
+        ),
+    ],
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -1 +1,2 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+transformers