Update README.md

README.md

@@ -27,20 +27,20 @@ NaturalQuery matches the state of the art models in text to sql for it's size an
 Here is a write up, small test done [here](https://chatdb.ai/post/naturalsql-vs-sqlcoder-for-text-to-sql).
 
 # Table of Contents
-1. [Benchmarks](#Benchmarks)
-    - [SQL-Eval on Novel Datasets](#SQL-Eval-on-Novel-Datasets)
-    - [SQL-Eval by Category](#SQL-Eval-by-Category)
-2. [Future Improvements](#Future-Improvements)
-3. [Usage](#Usage)
-    - [Installation](#Installation)
-    - [Loading the Model](#Loading-the-Model)
-    - [Generating Text](#Generating-Text)
-4. [SQL Generation Template](#SQL-Generation-Template)
-5. [Example SQL Output](#Example-SQL-Output)
-    - [Example Schemas](#Example-Schemas)
-    - [Example Queries](#Example-Queries)
-
-## **Benchmarks**
+1. [Benchmarks](#benchmarks)
+   - [SQL-Eval on novel datasets not seen in training](#sql-eval-on-novel-datasets-not-seen-in-training)
+   - [SQL-Eval by SQL Category](#sql-eval-by-sql-category)
+2. [Future Improvements](#future-improvements)
+3. [Usage](#usage)
+   - [Loading the Model](#loading-the-model)
+   - [Generating Text](#generating-text)
+4. [SQL Generation Template](#sql-generation-template)
+5. [Example SQL Output](#example-sql-output)
+   - [Example Schemas](#example-schemas)
+   - [Example SQL Outputs](#example-sql-outputs)
+  
+     
+## Benchmarks
 
 ## SQL-Eval on novel datasets not seen in training
 
@@ -48,7 +48,7 @@ Here is a write up, small test done [here](https://chatdb.ai/post/naturalsql-vs-
 
 <em>Big thanks to the [defog](https://huggingface.co/defog) team for open sourcing [sql-eval](https://github.com/defog-ai/sql-eval)</em>👏
 
-## **SQL-Eval by SQL Category**
+## SQL-Eval by SQL Category
 
 **NaturalQuery-6.7B-v0 matches or outperforms other industry leading models in multiple categories!**
 
@@ -56,14 +56,14 @@ Here is a write up, small test done [here](https://chatdb.ai/post/naturalsql-vs-
 
 _The **date** category will be a strong focus in the next iteration of `v1`._
 
-**Future Improvements in the next iteration**:
+## Future Improvements
 
 - Much larger training set
 - More complex schemas, questions, and queries
 - Strong focus on Date Queries
 - Reward modeling via DPO
 
-# **Usage**
+# Usage
 
 Make sure you have the correct version of the transformers library installed:
 
@@ -71,7 +71,7 @@ Make sure you have the correct version of the transformers library installed:
 pip install transformers==4.35.2
 ```
 
-### **Loading the Model**
+### Loading the Model
 
 Use the following Python code to load the model:
 
@@ -86,7 +86,7 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 ```
 
-### **Generating Text**
+### Generating Text
 
 To generate text, use the following Python code. [Here](https://gist.github.com/cfahlgren1/ba17f01cf688c4229686dc3dfb4d4549) is a full notebook with the SQL table prompt format to use.
 
@@ -105,7 +105,7 @@ print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
 ```
 
 
-# **SQL Generation Template**
+# SQL Generation Template
 
 ```
 ### Task 
@@ -125,9 +125,9 @@ Here is the SQL query that answers the question: `{natural language question}`
 '''sql
 ```
 
-# **Example SQL Output**
+# Example SQL Output
 
-### **Example Schemas**
+### Example Schemas
 
 ```sql
 CREATE TABLE users (
@@ -171,6 +171,7 @@ CREATE TABLE comments (
     user_id INTEGER REFERENCES users(user_id)
 );
 ```
+### Example SQL Outputs
 
 **Question**: **Show me the day with the most users joining**
 ```sql