Update README.md

README.md

@@ -13,7 +13,27 @@ datasets:
 pipeline_tag: text-generation
 ---
 
-# Uploaded  model
+# Gemma-2 2B Instruct fine-tuned on JSON dataset
+
+This model is a Gemma-2 2b model finetuned on the paraloq/json_data_extraction.
+
+The model was finetuned in order to extract data from a text according to a json schema.
+
+# Prompt
+
+The prompt used during training is:
+```py
+"""Below is a text paired with input that provides further context. Write JSON output that matches the schema to extract information.
+
+### Input:
+{input}
+
+### Schema:
+{schema}
+
+### Response:
+"""
+```
 
 - **Developed by:** bastienp
 - **License:** gemma