Update README.md

README.md

@@ -1,58 +1,52 @@
 ---
-base_model: Qwen/Qwen2.5-Coder-3B-Instruct
+base_model: unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit
 library_name: transformers
-model_name: onesql-qwen-3B
+model_name: onekq-ai/OneSQL-v0.2-Qwen-3B
 tags:
 - generated_from_trainer
+- unsloth
 - trl
 - sft
-licence: license
+licence: apache-2.0
+pipeline_tag: text-generation
 ---
 
-# Model Card for onesql-qwen-3B
+# Introduction
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+This model is the full-weight version of the adapter model [OneSQL-v0.1-Qwen-3B](https://huggingface.co/onekq-ai/OneSQL-v0.1-Qwen-3B).
 
-## Quick start
+# Quick start
 
-```python
-from transformers import pipeline
-
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="onekq-ai/onesql-qwen-3B", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
-
-## Training procedure
+To use this model, craft your prompt to start with your database schema in the form of **CREATE TABLE**, followed by your natural language query preceded by **--**.
+Make sure your prompt ends with **SELECT** in order for the model to finish the query for you.
 
- 
-
-
-This model was trained with SFT.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from peft import PeftModel
 
-### Framework versions
+model_name = "onekq-ai/OneSQL-v0.2-Qwen-3B"
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+tokenizer.padding_side = "left"
 
-- TRL: 0.17.0
-- Transformers: 4.51.3
-- Pytorch: 2.7.0
-- Datasets: 3.0.1
-- Tokenizers: 0.21.1
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer, return_full_text=False)
 
-## Citations
+prompt = """
+CREATE TABLE students (
+    id INTEGER PRIMARY KEY,
+    name TEXT,
+    age INTEGER,
+    grade TEXT
+);
 
+-- Find the three youngest students
+SELECT """
 
+result = generator(f"<|im_start|>system\nYou are a SQL expert. Return code only.<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n")[0]
+print(result["generated_text"])
+```
 
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
+The model response is the finished SQL query without **SELECT**
+```sql
+* FROM students ORDER BY age ASC LIMIT 3
 ```