Update README: correct Modelfile template and add ollama example

README.md

@@ -21,46 +21,45 @@ This is a specialized **Text-to-SQL** model fine-tuned from the **Microsoft Phi-
 - **Training Technique:** Fine-tuned using Lora with [Unsloth](https://github.com/unslothai/unsloth).
 - **Format:** GGUF (Ready for Ollama, LM Studio, and llama.cpp)
   - **phi-3-mini-4k-instruct.Q4_K_M.gguf** 
-  - **phi-3-mini-4k-instruct.Q5_K_M.gguf**
+  - **phi-3-mini-4k-instruct.Q5_K.gguf**
 
 ## Usage Instructions
 
 ### Ollama (Recommended)
 To deploy locally:
 
-1. Download the `.gguf` file.
+1. Download the `.gguf` file (Q4 or Q5).
 
 2. Create the Modelfile with the following instructions
 
 ```Dockerfile
 FROM ./phi-3-mini-4k-instruct.Q4_K_M.gguf
 
-SYSTEM """You are a specialized SQL assistant. Your goal is to produce valid SQL queries based on the provided schema and question. Output only the SQL code and nothing else."""
-
-TEMPLATE """<|system|>
-{{ .System }}<|end|>
-<|user|>
-{{ .Prompt }}<|end|>
+TEMPLATE """<s><|user|>
+Schema: {{ .System }}
+Question: {{ .Prompt }}<|end|>
 <|assistant|>
 """
 
+# Parameters for SQL stability
 PARAMETER stop "<|end|>"
-PARAMETER temperature 0.1
-PARAMETER num_ctx 2048
-PARAMETER repeat_penalty 1.2
+PARAMETER stop "<s>"
+PARAMETER stop "</s>"
+PARAMETER temperature 0.0
 ```
 
 3. Run ```ollama create phi3-sql-expert -f Modelfile```
 
-5. Run ```ollama run phi3-sql-expert```
+5. Run ```ollama run phi3-sql-expert "schema: CREATE TABLE table_name_7 (nba_draft VARCHAR, school VARCHAR) question: What was the NBA draft status for Northeast High School?"```
 
+6. The answer should be ```SELECT nba_draft FROM table_name_7 WHERE school = "Northeast"```
 
 ## Evaluation Data
-The model was fine-tuned on the sql-create-context dataset, focusing on:
+The model was fine-tuned on the [sql-create-context dataset](https://huggingface.co/datasets/b-mc2/sql-create-context), focusing on:
 
-- Mapping natural language to complex SELECT, WHERE, and JOIN statements.
+- Mapping natural language to SQL queries with SELECT, WHERE, and JOIN statements.
 - Understanding table schemas provided in the prompt.
-- Maintaining strict SQL syntax.
+- Maintaining strict SQL syntax in the response.
 
 ## Recommended Settings
 Temperature: 0.0 or 0.1 (SQL requires deterministic output).