update app

app.py

@@ -1,64 +1,39 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+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")
+# Model Info
+# model_path_local = '/Users/heykalsayid/Desktop/skill-academy/projects/ai-porto/deployment/app/model/eleutherai-finetuned'
+model_path_hf = 'paacamo/EleutherAI-pythia-1b-finetuned-nvidia-faq' # model from hugging face
 
+# set tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(model_path_hf)
+model = AutoModelForCausalLM.from_pretrained(model_path_hf)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# set pipeline for text generation
+text_generation = pipeline('text-generation', 
+                           model=model, 
+                           tokenizer=tokenizer,
+                           device=0 if torch.cuda.is_available() else -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})
+def respond_chat(message):
+    # prompt from model template for better response
+    prompt = f"###Question: {message} \n###Answer:"
 
-    response = ""
+    # response from the model
+    response = text_generation(prompt, max_new_tokens=100, do_sample=True)
+    return response[0]['generated_text'].split('###Answer:')[1]
 
-    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)",
-        ),
-    ],
+# start gradio interface
+demo = gr.Interface(
+    fn=respond_chat,
+    inputs='text',
+    outputs='text',
+    title="NVIDIA FAQ Chatbot",
+    description="Ask your question about NVIDIA products and services."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# main function to launch the app
+demo.launch(debug=True)

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+gradio==5.23.3
+