Update README.md

README.md

@@ -8,6 +8,29 @@ Hey I am CosmoGemma 👋 I can answer cosmology questions from astroph.CO resear
 This is a Gemma_2b_en fine-tuned on QA pairs (3.5k) generated from Cosmology and Nongalactic Astrophysics articles (arXiv astro-ph.CO) 
 from 2018-2022 and tested on QA pairs (1k) generated from 2023 articles, scoring over 75% accuracy.
 
+
+To generate an answer for a given question using this model, please use:
+
+import keras
+import keras_nlp
+
+gemma_lm = keras_nlp.models.CausalLM.from_preset("hf://sultan-hassan/CosmoGemma_2b_en")
+template = "Instruction:\n{instruction}\n\nResponse:\n{response}"
+
+Question = "write your question here"
+
+prompt = template.format(
+  instruction=Question,                                                                   
+  response="",
+  )
+out = gemma_lm.generate(prompt, max_length=1024)
+ind = out.index('Response') + len('Response')+2
+print ("Question:", Question)
+print ("Answer:", out[ind:])
+
+
+
+
 This is a [`Gemma` model](https://keras.io/api/keras_nlp/models/gemma) uploaded using the KerasNLP library and can be used with JAX, TensorFlow, and PyTorch backends.
 This model is related to a `CausalLM` task.