nawazmohd/RAZZER-AI

---

license: mit datasets:

• nvidia/Granary
• openai/healthbench
• syncora/developer-productivity-simulated-behavioral-data
• nvidia/Nemotron-CC-v2 language:
• ar
• hi
• en
• te
• ur metrics:
• accuracy
• bertscore
• bleu
• character
• code_eval base_model:
• google/gemma-3-270m
• Qwen/Qwen-Image-Edit
• drbaph/Qwen-Image-Edit-Mannequin-Clipper-LoRA
• xai-org/grok-2
• tencent/Hunyuan-MT-7B new_version: google/gemma-3-270m library_name: adapter-transformers tags:
• code
• music
• agent
• climate
• medical
• legal
• finance
• merge
• moe
• text-generation-inference ---import gradio as gr from transformers import pipeline from tensorflow.keras.applications.mobilenet_v2 import MobileNetV2, preprocess_input, decode_predictions from tensorflow.keras.preprocessing import image import numpy as np

----------------- Chatbot -----------------

chatbot = pipeline("text-generation", model="gpt2")

def chat_with_ai(user_input): response = chatbot(user_input, max_length=100, do_sample=True, top_k=50)[0]['generated_text'] return response

----------------- Image Recognition -----------------

model = MobileNetV2(weights="imagenet")

def classify_image(img): img = image.img_to_array(img) img = np.expand_dims(img, axis=0) img = preprocess_input(img) preds = model.predict(img) results = decode_predictions(preds, top=3)[0] return {label: float(prob) for (_, label, prob) in results}

----------------- Gradio App -----------------

with gr.Blocks() as demo: gr.Markdown("## 🤖 AI App: Chatbot + Image Recognition")

with gr.Tab("Chatbot"):
    chatbot_input = gr.Textbox(label="Type your message")
    chatbot_output = gr.Textbox(label="AI Response")
    chatbot_btn = gr.Button("Send")
    chatbot_btn.click(chat_with_ai, inputs=chatbot_input, outputs=chatbot_output)

with gr.Tab("Image Recognition"):
    img_input = gr.Image(type="pil", label="Upload an Image")
    img_output = gr.Label(label="Top Predictions")
    img_btn = gr.Button("Classify")
    img_btn.click(classify_image, inputs=img_input, outputs=img_output)

demo.launch()