rr

Dockerfile

@@ -23,4 +23,4 @@ EXPOSE 7860
 # ENV GRADIO_SERVER_PORT 7860
 
 # Run your script when the container launches
-CMD ["python", "app.py"]
+CMD ["python", "test.py"]

test.py

@@ -0,0 +1,43 @@
+# Use a pipeline as a high-level helper
+import transformers
+import torch
+from transformers import pipeline
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+pipe = pipeline("text-generation", model="tiiuae/falcon-180B")
+
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-180B")
+model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-180B")
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True,
+    device_map="auto",
+)
+
+def generate_headlines(topic):
+    sequences = pipeline(
+       f"Create at most 5 headlines that highlight {topic}. The headlines should be concise, attention-grabbing, and suitable for use in a news video.",
+        max_length=200,
+        do_sample=True,
+        top_k=10,
+        num_return_sequences=5,
+        eos_token_id=tokenizer.eos_token_id,
+    )
+    headlines = [seq['generated_text'] for seq in sequences]
+    return "\n".join(headlines)
+
+iface = gr.Interface(
+    fn=generate_headlines,
+    inputs=gr.inputs.Textbox(placeholder="Enter the topic"),
+    outputs="text",
+    examples=[["Climate Change"], ["AI Innovations"], ["Space Exploration"]]
+)
+
+iface.launch()