Update app.py

app.py

@@ -1,64 +1,128 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+# 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")
+# """
+# 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")
 
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# 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]})
+#     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})
+#     messages.append({"role": "user", "content": message})
 
-    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
+#     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
+#         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()
+
+
+
+
+
+
+
+import gradio as gr
+import os
+os.environ["KERAS_BACKEND"] = "tensorflow"                                                                           
+import keras
+import keras_nlp
+
+
+css = """
+html, body {
+    margin: 0;
+    padding: 0;
+    height: 100%;
+    overflow: hidden;
+}
+body::before {
+    content: '';
+    position: fixed;
+    top: 0;
+    left: 0;
+    width: 100vw;
+    height: 100vh;
+    background-image: url('https://stsci-opo.org/STScI-01J5E849R5W27ZZ2C3QAE9ET75.png');
+    background-size: cover;
+    background-repeat: no-repeat;
+    opacity: 0.65;             /* Faint background image */
+    background-position: center;
+    z-index: -1;    /* Keep the background behind text */
+}
+.gradio-container {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    height: 100vh;  /* Ensure the content is vertically centered */
+}
 """
-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()
+
+
+gemma_lm = keras_nlp.models.CausalLM.from_preset("hf://sultan-hassan/CosmoGemma_2b_en")
+
+def launch(input):
+    template = "Instruction:\n{instruction}\n\nResponse:\n{response}"
+    prompt = template.format(
+        instruction=input,                                                                   
+        response="",
+    )
+    out = gemma_lm.generate(prompt, max_length=1024)
+    ind = out.index('Response') + len('Response')+2
+    return out[ind:]
+
+iface = gr.Interface(launch,
+                     inputs="text",
+                     outputs="text",
+                     css=css,
+                     title="Hey I am CosmoGemma 👋 I can answer cosmology questions from astroph.CO research articles. Try me :)",
+                     description="Gemma_2b_en fine-tuned on QA pairs (~3.5k) generated from Cosmology and Nongalactic Astrophysics articles (arXiv astro-ph.CO) from 2018-2022 and tested on QA pairs (~1k) generated from 2023 articles, scoring over 75% accuracy.")
+
+iface.launch()