Instructions to use sriram882004/SQL-Socratic-Models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sriram882004/SQL-Socratic-Models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sriram882004/SQL-Socratic-Models",
	filename="gemma2/gemma2_9b__fft__base__masked/gguf/gemma2_9b__fft__base__masked_q8_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use sriram882004/SQL-Socratic-Models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sriram882004/SQL-Socratic-Models:Q8_0
# Run inference directly in the terminal:
llama-cli -hf sriram882004/SQL-Socratic-Models:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sriram882004/SQL-Socratic-Models:Q8_0
# Run inference directly in the terminal:
llama-cli -hf sriram882004/SQL-Socratic-Models:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf sriram882004/SQL-Socratic-Models:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf sriram882004/SQL-Socratic-Models:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf sriram882004/SQL-Socratic-Models:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sriram882004/SQL-Socratic-Models:Q8_0

Use Docker

docker model run hf.co/sriram882004/SQL-Socratic-Models:Q8_0

LM Studio
Jan
Ollama
How to use sriram882004/SQL-Socratic-Models with Ollama:
```
ollama run hf.co/sriram882004/SQL-Socratic-Models:Q8_0
```

Unsloth Studio

How to use sriram882004/SQL-Socratic-Models with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for sriram882004/SQL-Socratic-Models to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for sriram882004/SQL-Socratic-Models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sriram882004/SQL-Socratic-Models to start chatting

Docker Model Runner
How to use sriram882004/SQL-Socratic-Models with Docker Model Runner:
```
docker model run hf.co/sriram882004/SQL-Socratic-Models:Q8_0
```

Lemonade

How to use sriram882004/SQL-Socratic-Models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sriram882004/SQL-Socratic-Models:Q8_0

Run and chat with the model

lemonade run user.SQL-Socratic-Models-Q8_0

List all available models

lemonade list

SQL-Socratic-Models / README.md

sriram882004

Update README.md

92eb4c6 verified about 1 month ago

2.36 kB

license: mit

SQL Socratic Models

This repository contains fine-tuned large language models for Socratic SQL instruction in higher education, focusing on guiding learners through SQL concepts using structured reasoning rather than providing direct solutions.

Models

phi3_rq4
qwen25
gemma2

Method

Our approach is designed to support conceptual learning in STEM education through Socratic interaction:

Phase 1 (Data Construction):
SQL instruction data is augmented with Socratic prompts emphasizing:
- Question decomposition
- Conceptual hints
- Guided reasoning steps
Phase 2 (Fine-Tuning):
We apply full fine-tuning (FFT) on small, open-source LLMs with pedagogical constraints that explicitly discourage direct answer generation and instead promote:
- Conceptual scaffolding
- Incremental reasoning
- Learner-centered guidance
Phase 3 (Evaluation):
Models are evaluated using:
- BERTScore for semantic alignment with expected reasoning
- ROUGE-L to measure and control answer leakage (i.e., avoidance of direct SQL solutions)

Contributions

Fine-tuning across multiple architectures (Phi-3, Qwen2.5, Gemma2) for instructional SQL reasoning
Development of Socratic SQL prompting framework for higher education contexts
Evaluation of models on their ability to generate guidance without revealing final answers
Ablation study identifying factors that enable LLMs to mimic effective instructors through:
- Misconception-aware feedback
- Iterative questioning
- Structured reasoning support

Task

Given a natural language SQL question, the model generates:

Socratic reasoning steps
Conceptual hints and guiding questions
Intermediate decomposition of the problem

The model does NOT produce the final SQL query, ensuring alignment with instructional use in higher education settings.

This design supports:

Active learning
Conceptual understanding of SQL
Integration of database concepts into broader STEM curricula

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("sriram882004/SQL-Socratic-Models/phi3_rq4")
tokenizer = AutoTokenizer.from_pretrained("sriram882004/SQL-Socratic-Models/phi3_rq4")