abdulhayykhan

AbdiSQL-1.0

README

License: apache-2.0

Executive Summary

AbdiSQL-1.0 is an instruction-tuned, domain-expert Small Language Model (SLM) engineered to translate complex natural language questions into precise, executable SQLite queries based on provided database schemas.

Trained as Model #1 of the ABDI Platform (a 15-model ecosystem of specialized lightweight models), AbdiSQL proves that targeted domain adaptation can achieve high-fidelity code generation on consumer-grade and constrained hardware without requiring massive parameter overhead or multi-GPU server infrastructure.

Model Specifications

Table with columns: Attribute, Specification
Attribute	Specification
Model Name	AbdiSQL-1.0
Model Type	Causal Decoder-Only Transformer (Instruction-Tuned)
Base Model	`Qwen/Qwen2.5-Coder-1.5B-Instruct`
Target Dialect	SQLite
Total Parameters	1.54 Billion (1,543,714,816)
Trainable Parameters	1,089,536 (0.0705% of base parameters via LoRA)
Precision	16-bit Floating Point (`float16` merged release)
Context Length	Up to 32,768 tokens (optimized for schemas with multi-table DDL)
Training Hardware	1x NVIDIA Tesla T4 GPU (16 GB VRAM) on Google Colab
License	Apache 2.0

Intended Use & Domain Scope

Primary Use Cases

Natural Language to SQL Translation: Converting English questions into standard SQLite queries.
Database Schema Understanding: Accurately mapping entity mentions and relational logic to foreign keys, primary keys, and table columns.
Embedded & Edge Analytics: Low-latency on-device SQL generation for desktop apps, microservices, and localized business intelligence agents.

Scope Boundaries (v1.0)

In-Scope: Single-turn natural language queries against single or multi-table SQLite schemas involving JOIN, GROUP BY, ORDER BY, aggregates (COUNT, SUM, AVG), and subqueries.
Out-of-Scope (v1.0): Multi-dialect auto-translation (Postgres/MySQL specific functions), DDL schema mutations (ALTER TABLE, DROP), database performance index tuning, and multi-turn interactive disambiguation.

Dataset & Training Data

AbdiSQL was fine-tuned on cross-database examples derived from the prestigious Spider Text-to-SQL Benchmark (Yale University):

Cross-Database Diversity: 1,350 instruction pairs spanning over 160 distinct relational schemas across varied domains (e.g., healthcare, finance, academic records, sports, logistics).
Zero Schema Leakage: Training and evaluation splits are partitioned strictly by database schema (db_id), ensuring the model is evaluated on unseen database structures rather than memorized tables.
Prompt Formulation: Every sample formatted using the Qwen-2.5 ChatML template:
- System Prompt: Sets role and target dialect boundaries.
- User Input: Database DDL / schema definition paired with the natural language query.
- Assistant Target: Clean, syntactically valid SQLite code blocks.

Training Methodology

AbdiSQL-1.0 was trained using QLoRA (Quantized Low-Rank Adaptation) in 4-bit precision, maximizing parameter efficiency and stability on a single Tesla T4 GPU.

Hyperparameters

Table with columns: Hyperparameter, Value, Description / Rationale
Hyperparameter	Value	Description / Rationale
Quantization	4-bit NormalFloat (NF4)	Double quantization enabled to compress base weights
Compute Precision	`float16` / `float32`	Explicit FP32 casting for trainable LoRA layers on Turing architecture
LoRA Rank ( $r$ )	`8`	Balances representation capacity with small checkpoint footprint
LoRA Alpha ( $α$ )	`16`	Standard $2 \times r$ scaling factor
LoRA Dropout	`0.05`	Prevents over-specialization on training schemas
Target Modules	Attention & MLP projections	`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`
Epochs	`2`	Sufficient convergence across the 1,350 instruction samples
Learning Rate	`1e-4`	Tuned with Cosine annealing schedule
Warmup Ratio	`0.03`	Smooth gradient stabilization in initial steps
Optimizer	`paged_adamw_8bit`	Page-locked host memory prevents CUDA OOM spikes
Weight Merging	CPU RAM Offload	Full FP16 merge performed in system RAM to avoid VRAM allocation traps

Empirical Benchmark & Evaluation

Evaluation was performed using Execution Accuracy—the gold standard metric where generated SQL queries are executed against a live SQLite engine and their output record sets are strictly compared against ground-truth execution results (not superficial string matching).

Results on Held-Out Test Set (150 Unseen Cross-Database Queries)

Table with columns: Metric, Zero-Shot Base Model (Qwen2.5-Coder-1.5B), AbdiSQL-1.0 (Fine-Tuned), Delta
Metric	Zero-Shot Base Model (`Qwen2.5-Coder-1.5B`)	AbdiSQL-1.0 (Fine-Tuned)	Delta
Execution Accuracy	51.33% (77 / 150)	54.67% (82 / 150)	+3.34%
Syntax Validity Rate	64.00%	69.33% (104 / 150)	+5.33%
Spider Dev Split Accuracy	43.00%	47.00% (47 / 100)	+4.00%

Key Observations

Schema Grounding: Fine-tuning significantly eliminated hallucinated column and table names that the base model occasionally assumed from common SQL naming conventions.
SQLite Dialect Alignment: Greatly reduced SQLite-incompatible function usage (e.g., using STRFTIME instead of Postgres-specific date truncation).
Execution Robustness: Higher percentage of error-free syntax execution on first-pass generations.

Quick Start / How to Use

1. Standard Inference with Hugging Face `transformers`

python

import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "abdulhayykhan/AbdiSQL-1.0" # Load tokenizer and modeltokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(    model_id,    torch_dtype=torch.float16,    device_map="auto") # Define schema and your questionschema = """CREATE TABLE departments (    dept_id INTEGER PRIMARY KEY,    dept_name TEXT NOT NULL); CREATE TABLE employees (    emp_id INTEGER PRIMARY KEY,    name TEXT NOT NULL,    salary INTEGER,    dept_id INTEGER,    FOREIGN KEY (dept_id) REFERENCES departments(dept_id));"""question = "Find the name and salary of all employees in the 'Engineering' department who earn more than 75000." # Format prompt using model chat templatemessages = [    {        "role": "system",        "content": "You are AbdiSQL, a domain-expert language model specialized in generating precise SQLite queries from database schemas and questions."    },    {        "role": "user",        "content": f"{schema.strip()}\n\nQuestion: {question}"    }] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad():    outputs = model.generate(        **inputs,        max_new_tokens=128,        do_sample=False,        temperature=0.0,        pad_token_id=tokenizer.eos_token_id    ) generated_sql = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True).strip()print("Generated SQLite Query:\n", generated_sql)

2. Low-Resource Deployment (4-bit via `bitsandbytes` in < 2GB VRAM)

python

import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig model_id = "abdulhayykhan/AbdiSQL-1.0" bnb_config = BitsAndBytesConfig(    load_in_4bit=True,    bnb_4bit_quant_type="nf4",    bnb_4bit_compute_dtype=torch.float16) tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(    model_id,    quantization_config=bnb_config,    device_map="auto")

3. Edge / Local CPU Deployment via GGUF & `llama.cpp`

AbdiSQL-1.0 can be easily converted to GGUF format for real-time offline CPU execution using llama.cpp, Ollama, or LM Studio:

bash

# Clone llama.cppgit clone https://github.com/ggerganov/llama.cpp.gitcd llama.cpppip install -r requirements.txt # Convert downloaded HF weights to 4-bit GGUFpython convert_hf_to_gguf.py path/to/AbdiSQL-1.0 --outfile abdisql-1.0-q4_k_m.gguf --outtype q4_k_m

Limitations & Best Practices

Security & Read-Only Execution: Like all code-generating LLMs, queries generated by AbdiSQL should never be executed directly on production databases with write permissions. Always execute generated queries in a sandboxed, read-only session (PRAGMA query_only = ON; in SQLite).
Ultra-Complex Joins: Queries requiring 4+ table joins or recursive CTEs may occasionally require human verification or query refinement.
Dialect Specificity: Optimized specifically for SQLite syntax. Dialect-specific keywords from SQL Server, Oracle, or PostgreSQL are not guaranteed to be compatible.

Citation & Acknowledgements

If you use AbdiSQL-1.0 in your research or application, please cite:

bibtex

@misc{abdisql2026,  author = {Abdul Hayy Khan},  title = {AbdiSQL-1.0: A Domain-Specialized Small Language Model for Text-to-SQL},  year = {2026},  publisher = {Hugging Face},  howpublished = {\url{https://huggingface.co/abdulhayykhan/AbdiSQL-1.0}}}

Special acknowledgment to:

The Yale LILY Lab for the Spider Benchmark.
The Qwen Team (Alibaba Cloud) for the excellent Qwen2.5-Coder foundation series.
The ABDI Platform initiative for pioneering accessible domain-specialized SLMs.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

abdulhayykhan

Model Tree

Base

Qwen/Qwen2.5-Coder-1.5B-Instruct

Fine-tuned

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Executive Summary

Model Specifications

Table with columns: Attribute, Specification
Attribute	Specification
Model Name	AbdiSQL-1.0
Model Type	Causal Decoder-Only Transformer (Instruction-Tuned)
Base Model	`Qwen/Qwen2.5-Coder-1.5B-Instruct`
Target Dialect	SQLite
Total Parameters	1.54 Billion (1,543,714,816)
Trainable Parameters	1,089,536 (0.0705% of base parameters via LoRA)
Precision	16-bit Floating Point (`float16` merged release)
Context Length	Up to 32,768 tokens (optimized for schemas with multi-table DDL)
Training Hardware	1x NVIDIA Tesla T4 GPU (16 GB VRAM) on Google Colab
License	Apache 2.0

Intended Use & Domain Scope

Primary Use Cases

Natural Language to SQL Translation: Converting English questions into standard SQLite queries.
Database Schema Understanding: Accurately mapping entity mentions and relational logic to foreign keys, primary keys, and table columns.
Embedded & Edge Analytics: Low-latency on-device SQL generation for desktop apps, microservices, and localized business intelligence agents.

Scope Boundaries (v1.0)

In-Scope: Single-turn natural language queries against single or multi-table SQLite schemas involving JOIN, GROUP BY, ORDER BY, aggregates (COUNT, SUM, AVG), and subqueries.
Out-of-Scope (v1.0): Multi-dialect auto-translation (Postgres/MySQL specific functions), DDL schema mutations (ALTER TABLE, DROP), database performance index tuning, and multi-turn interactive disambiguation.

Dataset & Training Data

AbdiSQL was fine-tuned on cross-database examples derived from the prestigious Spider Text-to-SQL Benchmark (Yale University):

Cross-Database Diversity: 1,350 instruction pairs spanning over 160 distinct relational schemas across varied domains (e.g., healthcare, finance, academic records, sports, logistics).
Zero Schema Leakage: Training and evaluation splits are partitioned strictly by database schema (db_id), ensuring the model is evaluated on unseen database structures rather than memorized tables.
Prompt Formulation: Every sample formatted using the Qwen-2.5 ChatML template:
- System Prompt: Sets role and target dialect boundaries.
- User Input: Database DDL / schema definition paired with the natural language query.
- Assistant Target: Clean, syntactically valid SQLite code blocks.

Training Methodology

AbdiSQL-1.0 was trained using QLoRA (Quantized Low-Rank Adaptation) in 4-bit precision, maximizing parameter efficiency and stability on a single Tesla T4 GPU.

Hyperparameters

Table with columns: Hyperparameter, Value, Description / Rationale
Hyperparameter	Value	Description / Rationale
Quantization	4-bit NormalFloat (NF4)	Double quantization enabled to compress base weights
Compute Precision	`float16` / `float32`	Explicit FP32 casting for trainable LoRA layers on Turing architecture
LoRA Rank ( $r$ )	`8`	Balances representation capacity with small checkpoint footprint
LoRA Alpha ( $α$ )	`16`	Standard $2 \times r$ scaling factor
LoRA Dropout	`0.05`	Prevents over-specialization on training schemas
Target Modules	Attention & MLP projections	`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`
Epochs	`2`	Sufficient convergence across the 1,350 instruction samples
Learning Rate	`1e-4`	Tuned with Cosine annealing schedule
Warmup Ratio	`0.03`	Smooth gradient stabilization in initial steps
Optimizer	`paged_adamw_8bit`	Page-locked host memory prevents CUDA OOM spikes
Weight Merging	CPU RAM Offload	Full FP16 merge performed in system RAM to avoid VRAM allocation traps

Empirical Benchmark & Evaluation

Results on Held-Out Test Set (150 Unseen Cross-Database Queries)

Table with columns: Metric, Zero-Shot Base Model (Qwen2.5-Coder-1.5B), AbdiSQL-1.0 (Fine-Tuned), Delta
Metric	Zero-Shot Base Model (`Qwen2.5-Coder-1.5B`)	AbdiSQL-1.0 (Fine-Tuned)	Delta
Execution Accuracy	51.33% (77 / 150)	54.67% (82 / 150)	+3.34%
Syntax Validity Rate	64.00%	69.33% (104 / 150)	+5.33%
Spider Dev Split Accuracy	43.00%	47.00% (47 / 100)	+4.00%

Key Observations

Schema Grounding: Fine-tuning significantly eliminated hallucinated column and table names that the base model occasionally assumed from common SQL naming conventions.
SQLite Dialect Alignment: Greatly reduced SQLite-incompatible function usage (e.g., using STRFTIME instead of Postgres-specific date truncation).
Execution Robustness: Higher percentage of error-free syntax execution on first-pass generations.

Quick Start / How to Use

1. Standard Inference with Hugging Face `transformers`

python

import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "abdulhayykhan/AbdiSQL-1.0" # Load tokenizer and modeltokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(    model_id,    torch_dtype=torch.float16,    device_map="auto") # Define schema and your questionschema = """CREATE TABLE departments (    dept_id INTEGER PRIMARY KEY,    dept_name TEXT NOT NULL); CREATE TABLE employees (    emp_id INTEGER PRIMARY KEY,    name TEXT NOT NULL,    salary INTEGER,    dept_id INTEGER,    FOREIGN KEY (dept_id) REFERENCES departments(dept_id));"""question = "Find the name and salary of all employees in the 'Engineering' department who earn more than 75000." # Format prompt using model chat templatemessages = [    {        "role": "system",        "content": "You are AbdiSQL, a domain-expert language model specialized in generating precise SQLite queries from database schemas and questions."    },    {        "role": "user",        "content": f"{schema.strip()}\n\nQuestion: {question}"    }] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad():    outputs = model.generate(        **inputs,        max_new_tokens=128,        do_sample=False,        temperature=0.0,        pad_token_id=tokenizer.eos_token_id    ) generated_sql = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True).strip()print("Generated SQLite Query:\n", generated_sql)

import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "abdulhayykhan/AbdiSQL-1.0" # Load tokenizer and modeltokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(    model_id,    torch_dtype=torch.float16,    device_map="auto") # Define schema and your questionschema = """CREATE TABLE departments (    dept_id INTEGER PRIMARY KEY,    dept_name TEXT NOT NULL); CREATE TABLE employees (    emp_id INTEGER PRIMARY KEY,    name TEXT NOT NULL,    salary INTEGER,    dept_id INTEGER,    FOREIGN KEY (dept_id) REFERENCES departments(dept_id));"""question = "Find the name and salary of all employees in the 'Engineering' department who earn more than 75000." # Format prompt using model chat templatemessages = [    {        "role": "system",        "content": "You are AbdiSQL, a domain-expert language model specialized in generating precise SQLite queries from database schemas and questions."    },    {        "role": "user",        "content": f"{schema.strip()}\n\nQuestion: {question}"    }] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad():    outputs = model.generate(        **inputs,        max_new_tokens=128,        do_sample=False,        temperature=0.0,        pad_token_id=tokenizer.eos_token_id    ) generated_sql = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True).strip()print("Generated SQLite Query:\n", generated_sql)

2. Low-Resource Deployment (4-bit via `bitsandbytes` in < 2GB VRAM)

python

import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig model_id = "abdulhayykhan/AbdiSQL-1.0" bnb_config = BitsAndBytesConfig(    load_in_4bit=True,    bnb_4bit_quant_type="nf4",    bnb_4bit_compute_dtype=torch.float16) tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(    model_id,    quantization_config=bnb_config,    device_map="auto")

import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig model_id = "abdulhayykhan/AbdiSQL-1.0" bnb_config = BitsAndBytesConfig(    load_in_4bit=True,    bnb_4bit_quant_type="nf4",    bnb_4bit_compute_dtype=torch.float16) tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(    model_id,    quantization_config=bnb_config,    device_map="auto")

3. Edge / Local CPU Deployment via GGUF & `llama.cpp`

AbdiSQL-1.0 can be easily converted to GGUF format for real-time offline CPU execution using llama.cpp, Ollama, or LM Studio:

bash

# Clone llama.cppgit clone https://github.com/ggerganov/llama.cpp.gitcd llama.cpppip install -r requirements.txt # Convert downloaded HF weights to 4-bit GGUFpython convert_hf_to_gguf.py path/to/AbdiSQL-1.0 --outfile abdisql-1.0-q4_k_m.gguf --outtype q4_k_m

# Clone llama.cppgit clone https://github.com/ggerganov/llama.cpp.gitcd llama.cpppip install -r requirements.txt # Convert downloaded HF weights to 4-bit GGUFpython convert_hf_to_gguf.py path/to/AbdiSQL-1.0 --outfile abdisql-1.0-q4_k_m.gguf --outtype q4_k_m

Limitations & Best Practices

Security & Read-Only Execution: Like all code-generating LLMs, queries generated by AbdiSQL should never be executed directly on production databases with write permissions. Always execute generated queries in a sandboxed, read-only session (PRAGMA query_only = ON; in SQLite).
Ultra-Complex Joins: Queries requiring 4+ table joins or recursive CTEs may occasionally require human verification or query refinement.
Dialect Specificity: Optimized specifically for SQLite syntax. Dialect-specific keywords from SQL Server, Oracle, or PostgreSQL are not guaranteed to be compatible.

Citation & Acknowledgements

If you use AbdiSQL-1.0 in your research or application, please cite:

bibtex

@misc{abdisql2026,  author = {Abdul Hayy Khan},  title = {AbdiSQL-1.0: A Domain-Specialized Small Language Model for Text-to-SQL},  year = {2026},  publisher = {Hugging Face},  howpublished = {\url{https://huggingface.co/abdulhayykhan/AbdiSQL-1.0}}}

@misc{abdisql2026,  author = {Abdul Hayy Khan},  title = {AbdiSQL-1.0: A Domain-Specialized Small Language Model for Text-to-SQL},  year = {2026},  publisher = {Hugging Face},  howpublished = {\url{https://huggingface.co/abdulhayykhan/AbdiSQL-1.0}}}

Special acknowledgment to:

The Yale LILY Lab for the Spider Benchmark.
The Qwen Team (Alibaba Cloud) for the excellent Qwen2.5-Coder foundation series.
The ABDI Platform initiative for pioneering accessible domain-specialized SLMs.

AbdiSQL-1.0

README

Executive Summary

Model Specifications

Intended Use & Domain Scope

Primary Use Cases

Scope Boundaries (v1.0)

Dataset & Training Data

Training Methodology

Hyperparameters

Empirical Benchmark & Evaluation

Results on Held-Out Test Set (150 Unseen Cross-Database Queries)

Key Observations

Quick Start / How to Use

1. Standard Inference with Hugging Face transformers

2. Low-Resource Deployment (4-bit via bitsandbytes in < 2GB VRAM)

3. Edge / Local CPU Deployment via GGUF & llama.cpp

Limitations & Best Practices

Citation & Acknowledgements

Explore FriendliAI today

README

Executive Summary

Model Specifications

Intended Use & Domain Scope

Primary Use Cases

Scope Boundaries (v1.0)

Dataset & Training Data

Training Methodology

Hyperparameters

Empirical Benchmark & Evaluation

Results on Held-Out Test Set (150 Unseen Cross-Database Queries)

Key Observations

Quick Start / How to Use

1. Standard Inference with Hugging Face transformers

2. Low-Resource Deployment (4-bit via bitsandbytes in < 2GB VRAM)

3. Edge / Local CPU Deployment via GGUF & llama.cpp

Limitations & Best Practices

Citation & Acknowledgements

1. Standard Inference with Hugging Face `transformers`

2. Low-Resource Deployment (4-bit via `bitsandbytes` in < 2GB VRAM)

3. Edge / Local CPU Deployment via GGUF & `llama.cpp`

1. Standard Inference with Hugging Face `transformers`

2. Low-Resource Deployment (4-bit via `bitsandbytes` in < 2GB VRAM)

3. Edge / Local CPU Deployment via GGUF & `llama.cpp`