Update app.py

app.py

@@ -1,64 +1,26 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+os.environ["KERAS_BACKEND"] = "tensorflow"                                                                           
+import keras
+import keras_nlp
 
-"""
-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("sultan-hassan/CosmoGemma_2b_en")
 
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+gemma_lm = keras_nlp.models.CausalLM.from_preset("hf://sultan-hassan/CosmoGemma_2b_en")
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def launch(input):
+    template = "Instruction:\n{instruction}\n\nResponse:\n{response}"
+    prompt = template.format(
+        instruction=input,                                                                   
+        response="",
+    )
+    out = gemma_lm.generate(prompt, max_length=256)
+    ind = out.index('Response') + len('Response')+2
+    return out[ind:]
 
-    messages.append({"role": "user", "content": message})
+iface = gr.Interface(launch,
+                     inputs="text",
+                     outputs="text")
 
-    response = ""
+iface.launch()
 
-    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()