app.py added

app.py

@@ -0,0 +1,17 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Load the model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1")
+model = AutoModelForCausalLM.from_pretrained("Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1").to("cuda")
+
+def generate_text(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    with torch.no_grad():
+        output = model.generate(inputs["input_ids"], max_new_tokens=50)
+    return tokenizer.decode(output[0], skip_special_tokens=True)
+
+# Launch Gradio app
+interface = gr.Interface(fn=generate_text, inputs="text", outputs="text")
+interface.launch()