Update README.md

README.md

@@ -23,13 +23,13 @@ tags:
 
 
 
-- **Developed by:** [More Information Needed]
+- **Developed by:** Srujana Madiraju 
 - **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
+- **Model type:** Fine tuned gemma2b model on NL-SQL dataset
+- **Language(s) (NLP):** python 
 - **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Finetuned from model [optional]:** Google Gemma 2b 
 
 ### Model Sources [optional]
 
@@ -41,7 +41,7 @@ tags:
 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+Use this fine tuned model for converting natural language to sql query in any software application according to one's use case. 
 
 ### Direct Use
 
@@ -77,6 +77,28 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 Use the code below to get started with the model.
 
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+import torch
+
+# Set your base model and adapter repo
+base_model_id = "google/gemma-2b"
+adapter_repo = "srujanamadiraju/nl-sql-gemma2b"
+
+# Load tokenizer (from adapter repo)
+tokenizer = AutoTokenizer.from_pretrained(adapter_repo)
+
+# Load base model (same as used during fine-tuning)
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_model_id,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+# Load LoRA adapter on top of base model
+model = PeftModel.from_pretrained(base_model, adapter_repo)
+model.eval()
+
 [More Information Needed]
 
 ## Training Details