Update app.py

app.py

@@ -1,19 +1,20 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-"""
-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")
+# Initialize Hugging Face Inference API client
+hf_client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# Load the second model
+local_model_name = "codewithdark/latent-recurrent-depth-lm"
+tokenizer = AutoTokenizer.from_pretrained(local_model_name)
+model = AutoModelForCausalLM.from_pretrained(local_model_name)
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+def generate_response(
+    message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p, model_choice
 ):
     messages = [{"role": "system", "content": system_message}]
 
@@ -22,43 +23,37 @@ def respond(
             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
+    if model_choice == "Zephyr-7B (API)":
+        response = ""
+        for message in hf_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
+    else:
+        input_text = tokenizer.apply_chat_template(messages, return_tensors="pt").to(device)
+        output = model.generate(input_text, max_length=max_tokens, temperature=temperature, top_p=top_p)
+        response = tokenizer.decode(output[0], skip_special_tokens=True)
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
-    respond,
+    generate_response,
     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=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
+        gr.Radio(["Zephyr-7B (API)", "Latent Recurrent Depth LM"], value="Zephyr-7B (API)", label="Select Model"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()