updatef for llmam

app.py

@@ -2,66 +2,50 @@ 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
+For more information on `huggingface_hub` Inference API support, check:
+https://huggingface.co/docs/huggingface_hub/en/guides/inference
 """
-# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-client = InferenceClient('one1cat/FineTunes_LLM_CFR_49')
+# Initialize the Inference API Client with your model
+client = InferenceClient("one1cat/FineTunes_LLM_CFR_49")
 
 
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    """
+    Generates responses using the fine-tuned CFR 49 model.
+    """
 
-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})
+    # Format prompt
+    prompt = f"{system_message}\n\nUser: {message}\n\nAssistant:"
 
+    # Generate response
     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
+    try:
+        for token in client.text_generation(
+            prompt,
+            max_new_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+            stream=True,  # Enables token streaming
+        ):
+            response += token
+            yield response
 
-        response += token
-        yield response
+    except Exception as e:
+        yield f"Error: {str(e)}"
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio Chat Interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are an AI trained on CFR 49 regulations.", 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=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()