Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit
+base_model: unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit
 tags:
 - text-generation-inference
 - transformers
@@ -13,7 +13,7 @@ language:
 
 # About Model 
 
-Fine-tuning is used to convert SQL language into natural language, making it easier for users to understand the business meaning of SQL queries. This fine-tuned model is based on the unsloth framework 和 uses the DeepSeek-R1-Distill-Llama-8B pre-trained model under unsloth.
+Fine-tuning is used to convert SQL language into natural language, making it easier for users to understand the business meaning of SQL queries. This fine-tuned model is based on the unsloth framework AND uses the DeepSeek-R1-Distill-Llama-8B pre-trained model under unsloth.
 
 
 # DataSet 
@@ -42,36 +42,58 @@ This is a complex customer analysis query used to test the understanding of the
 query1 = """
 ```sql
 SELECT
-    c.customer_id,
-    c.name AS customer_name,
-    COUNT(o.order_id) AS total_orders,
-    SUM(o.total_amount) AS total_spent,
-    AVG(o.total_amount) AS avg_order_value,
-    MAX(o.order_date) AS last_order_date
-FROM customers c
-JOIN orders o ON c.customer_id = o.customer_id
-LEFT JOIN order_items oi ON o.order_id = oi.order_id
-WHERE o.order_date >= '2024-01-01'
-GROUP BY c.customer_id, c.name
-ORDER BY total_spent DESC
-LIMIT 10;
+    pc.category_name,
+    p.product_name,
+    COUNT(DISTINCT o.customer_id) AS unique_customers,
+    COUNT(oi.order_id) AS total_sales,
+    SUM(oi.quantity) AS total_quantity_sold,
+    ROUND(AVG(oi.unit_price), 2) AS avg_selling_price,
+    SUM(oi.quantity * oi.unit_price) AS total_revenue,
+    ROUND(SUM(oi.quantity * oi.unit_price) / COUNT(DISTINCT o.customer_id), 2) AS revenue_per_customer,
+    MAX(o.order_date) AS last_sale_date,
+    MIN(o.order_date) AS first_sale_date
+FROM product_categories pc
+JOIN products p ON pc.category_id = p.category_id
+JOIN order_items oi ON p.product_id = oi.product_id
+JOIN orders o ON oi.order_id = o.order_id
+WHERE
+    o.order_date >= '2024-01-01'
+    AND o.order_status = 'completed'
+GROUP BY
+    pc.category_name,
+    p.product_name
+HAVING
+    total_revenue > 10000
+ORDER BY
+    total_revenue DESC,
+    unique_customers DESC
+LIMIT 15;
 ```
 Explain use case of this query.
 """
 
-## Pre-training inference results:
+<think>
+CREATE TABLE product_categories (category_name VARCHAR, product_name VARCHAR, customer_id INT, order_id INT, order_date DATETIME, status VARCHAR)  
+FROM product_categories 
+JOIN products 
+JOIN order_items 
+JOIN orders 
+WHERE order_date >= '2024-01-01' AND order_status = 'completed' 
+GROUP BY category_name, product_name 
+HAVING total_revenue > 10000 
 
-The SQL query is designed to analyze customer data from the orders placed in January 2024. It aggregates information such as the number of orders, total spending, average order value, and the last order date for each customer. The results are sorted by total spending in descending order, allowing the identification of the top 10 customers based on their spending. This is useful for marketing or sales teams to target high-spending customers for promotions or personalized campaigns. The LEFT JOIN with order_items ensures that all customers, including those with pending or incomplete orders, are included in the results.<｜end▁of▁sentence｜>
-
-## Inference results after training:
-Show customer id, customer name, total orders, total spent, average order value，last order date for top 10 customers by total spent.< | end▁of▁sentence｜>
+This query analyzes the relationship between product categories and customer orders to identify categories and products with the highest revenue in completed orders since 2024. It can help a business understand which products are generating significant revenue and which products are performing well in the category to inform inventory planning and pricing strategies.
+</think>
+Below is the business use case for the query:
 
+### Use Case:
+This query analyzes the relationship between product categories and customer orders to identify categories and products with the highest revenue in completed orders since 2024. It can help a business understand which products are generating significant revenue in the category and which products are performing well in the category to inform inventory planning and pricing strategies.<｜end▁of▁sentence｜>
 
 # Model  Download
 
 | **Model**                        | **Base Model**                                               | **下载**                                                 |
 | -------------------------------- | ------------------------------------------------------------ | ------------------------------------------------------------ |
-| DeepSeek-R1-Distill-Llama-sql-4B | [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) | [🤗 HuggingFace](https://huggingface.co/jackcwf/DeepSeek-R1-Distill-Llama-4bit-sql-model/raw/main/unsloth.Q4_K_M.gguf) |
+| DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit | [Qwen-1.5B](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit) | [🤗 HuggingFace](https://huggingface.co/jackcwf/DeepSeek-R1-Distill-Llama-4bit-sql-model/raw/main/unsloth.Q4_K_M.gguf) |
 
 
 # Usage
@@ -81,9 +103,9 @@ If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](ht
 
 # Uploaded  model
 
-- **Developed by:** jackcwf
+- **Developed by:** datalabs-ai
 - **License:** apache-2.0
-- **Finetuned from model :** unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit
+- **Finetuned from model :** unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit