Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: unsloth/Phi-3.5-mini-instruct
+base_model: microsoft/Phi-3.5-mini-instruct
 language:
 - en
 license: apache-2.0
@@ -9,14 +9,31 @@ tags:
 - unsloth
 - llama
 - trl
+- ollama
+- text2sql
+datasets:
+- Clinton/Text-to-sql-v1
 ---
 
-# Uploaded  model
+# Phi3.5 text2sql
 
 - **Developed by:** cahaj
 - **License:** apache-2.0
-- **Finetuned from model :** unsloth/Phi-3.5-mini-instruct
+- **Finetuned from model :** microsoft/Phi-3.5-mini-instruct
+- **Dataset :** Clinton/Text-to-sql-v1
+- **LoRa :** 64/64
+
+## Training template
+```py
+prompt = """<|system|>
+You are a SQL database query generator. User provides you with sql tables schemas paired with instruction that describes a task. Using valid SQLite, write a response that appropriately completes the request for the provided tables.<|end|>
+<|user|>
+{}
+SQL table schema: {}<|end|>
+<|assistant|>
+{}<|end|>"""
+```
 
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)