wowww

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Load model and tokenizer
+model_id = "deepseek-ai/DeepSeek-R1"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+
+# Inference function
+def generate(prompt, max_new_tokens=256, temperature=0.7, top_p=0.95):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    output = model.generate(
+        **inputs,
+        max_new_tokens=max_new_tokens,
+        temperature=temperature,
+        top_p=top_p,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 🚀 DeepSeek-R1 - Hugging Face Space Demo")
+    
+    with gr.Row():
+        prompt = gr.Textbox(label="Prompt", placeholder="Ask me anything...")
+    
+    with gr.Row():
+        max_tokens = gr.Slider(64, 1024, value=256, step=16, label="Max new tokens")
+        temperature = gr.Slider(0.1, 1.5, value=0.7, step=0.1, label="Temperature")
+        top_p = gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p")
+
+    output = gr.Textbox(label="Generated Text")
+
+    generate_btn = gr.Button("Generate")
+    generate_btn.click(fn=generate, inputs=[prompt, max_tokens, temperature, top_p], outputs=output)
+
+demo.launch()