Updated Readme

README.md

@@ -1,6 +1,14 @@
-
-license: apache-2.0tags:  - sql  - text-to-sql  - fine-tuned  - qwen
-Qwen2.5-Coder-3B-Instruct Merged SQL Model
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- Qwen/Qwen2.5-Coder-3B-Instruct
+tags:
+- text-to-sql
+- fine-tuned
+- qwen
+---
 This is a fine-tuned version of Qwen/Qwen2.5-Coder-3B-Instruct for generating SQL queries from natural language questions. The model was fine-tuned using LoRA (r=16) on a subset of the Spider dataset and merged into a standalone model, eliminating the need for the peft library during inference.
 Usage
 To use the model for SQL query generation:
@@ -8,7 +16,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
 # Load model and tokenizer
-model_name = "your-username/qwen-merged-sql-finetuned"  # Replace with your repo ID
+model_name = "Piyush026/Qwen2.5-Coder-3B-sql-finetuned"  # Replace with your repo ID
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -33,9 +41,9 @@ outputs = model.generate(**inputs, max_length=200)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 
-Training Details
+## Training Details
 
 Base Model: Qwen/Qwen2.5-Coder-3B-Instruct
 Fine-Tuning: LoRA (r=16, lora_alpha=32, lora_dropout=0.05) on a 1000-sample subset of the Spider dataset.
 Environment: Lightning AI Studio with Tesla T4 GPU.
-Merged Model: The LoRA adapters were merged into the base model using merge_and_unload for standalone inference.
+Merged Model: The LoRA adapters were merged into the base model using merge_and_unload for standalone inference.