Update app.py

app.py

@@ -1,70 +1,63 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+# Pick one of the models from your collection:
+MODEL_NAME = "NextGLab/oransight-20-gemma-2b"  # <-- edit this to whichever in your collection
+
+@torch.inference_mode()
+def load_model():
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+    model = AutoModelForCausalLM.from_pretrained(
+        MODEL_NAME,
+        device_map="auto",
+        torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32
+    )
+    pipe = pipeline(
+        "text-generation",
+        model=model,
+        tokenizer=tokenizer,
+        device=model.device,
+    )
+    return pipe
+
+pipe = load_model()
+
+# Simple chatbot fn
+def chat(message, history, max_new_tokens=256, temperature=0.7):
+    prompt = message
+    outputs = pipe(
+        prompt,
+        max_new_tokens=max_new_tokens,
         temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
-)
+        do_sample=True,
+        pad_token_id=pipe.tokenizer.eos_token_id,
+    )
+    text = outputs[0]["generated_text"]
+    # Hugging Face pipeline often echos input text → remove
+    return text[len(prompt):].strip()
 
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
+    gr.Markdown(f"# 🤖 Oransight‑20‑Gemma Demo\nModel: **{MODEL_NAME}**")
+    
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="Your message")
+    send = gr.Button("Send")
+    clear = gr.Button("Clear")
+    
+    max_tokens = gr.Slider(50, 600, value=256, step=10, label="Max new tokens")
+    temperature = gr.Slider(0.1, 1.5, value=0.7, step=0.1, label="Temperature")
+    
+    state = gr.State([])
+    
+    def respond(message, history, max_tokens, temperature):
+        response = chat(message, history, max_tokens, temperature)
+        history.append((message, response))
+        return history, history, ""
+    
+    send.click(respond, [msg, state, max_tokens, temperature], [chatbot, state, msg])
+    msg.submit(respond, [msg, state, max_tokens, temperature], [chatbot, state, msg])
+    clear.click(lambda: ([], []), None, [chatbot, state])
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()