sakthi54321/power_ai

App.py

@@ -1,47 +0,0 @@
-import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
-
-model_id = "sakthi54321/power_ai"
-
-# Load model + tokenizer
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
-    device_map="auto"
-)
-
-# Simple function: one input → one output
-def ask_model(prompt):
-    # force very direct answer
-    input_text = f"Question: {prompt}\nAnswer:"
-    
-    inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
-    outputs = model.generate(
-        **inputs,
-        max_new_tokens=800,   # keep answers short
-        pad_token_id=tokenizer.eos_token_id,
-        do_sample=True,
-        top_p=0.9,
-        temperature=0.7
-    )
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-    # only take the text after "Answer:"
-    if "Answer:" in response:
-        response = response.split("Answer:")[-1].strip()
-    
-    return response
-
-
-# Gradio UI (straightforward)
-demo = gr.Interface(
-    fn=ask_model,
-    inputs=gr.Textbox(label="Ask something", placeholder="Type your question here..."),
-    outputs=gr.Textbox(label="Model Response"),
-    title="🤖 Power AI",
-    description="Straightforward Q&A with your trained model"
-)
-
-demo.launch()

app.py

@@ -1,48 +1,70 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
+from huggingface_hub import InferenceClient
 
-model_id = "sakthi54321/power_ai"
 
-# Load model + tokenizer
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
-    device_map="auto"
-)
+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 = ""
 
-# Simple function: one input → one output
-def ask_model(prompt):
-    # force very direct answer
-    input_text = f"Question: {prompt}\nAnswer:"
-    
-    inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
-    outputs = model.generate(
-        **inputs,
-        max_new_tokens=800,   # keep answers short
-        pad_token_id=tokenizer.eos_token_id,
-        do_sample=True,
-        top_p=0.9,
-        temperature=0.7
-    )
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-    # only take the text after "Answer:"
-    if "Answer:" in response:
-        response = response.split("Answer:")[-1].strip()
-    
-    return response
-
-
-
-# Gradio UI (straightforward)
-demo = gr.Interface(
-    fn=ask_model,
-    inputs=gr.Textbox(label="Ask something", placeholder="Type your question here..."),
-    outputs=gr.Textbox(label="Model Response"),
-    title="🤖 Power AI",
-    description="Straightforward Q&A with your trained model"
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        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)",
+        ),
+    ],
 )
 
-demo.launch()
+with gr.Blocks() as demo:
+    with gr.Sidebar():
+        gr.LoginButton()
+    chatbot.render()
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -1,4 +0,0 @@
-transformers
-torch
-accelerate
-gradio