sirunchained

text-to-sql-model-v2

🚀 Model Description

This is Version 2 of the sirunchained/text-to-sql-model, fine-tuned from google/gemma-3-270m-it for Text-to-SQL generation.
In this version, the model is merged with the LoRA adapter – you can load it directly with pipeline() (no PEFT required).

Key improvements in v2:

Table with columns: Feature, v1 (LoRA Adapter), v2 (Merged)
Feature	v1 (LoRA Adapter)	v2 (Merged)
Load method	Required PEFT + base model	Direct `pipeline()`
Model size	~10 MB (adapter only)	~536 MB (full model)
Inference speed	Slower (requires adapter load)	Faster
Ease of use	Complex	Simple
Performance	89.7% accuracy	✅ Same

🧠 Task

Text-to-SQL Generation
Converts natural language questions into SQL queries. Supports:

✅ SELECT queries (with JOINs, aggregations, subqueries)
✅ INSERT operations
✅ UPDATE operations
✅ DELETE operations (currently weak at this)

📊 Training Details

Table with columns: Item, Value
Item	Value
Base Model	`google/gemma-3-270m-it`
Fine-tuning Method	LoRA + 4-bit quantization (QLoRA)
Framework	`trl` (SFTTrainer)
Dataset	`sirunchained/text-to-sql-dataset` (4518 samples training, 200 validation, 200 test)
Training Epochs	5
Batch Size	32

📈 Training Performance

Table with columns: Epoch, Training Loss, Validation Loss, Mean Token Accuracy
Epoch	Training Loss	Validation Loss	Mean Token Accuracy
1	0.800	0.700	83.8%
2	0.650	0.680	84.2%
3	0.500	0.650	84.6%
4	0.350	0.640	85.1%

Best validation loss was achieved at epoch 4 & 5 (0.640).
Highest mean token accuracy on validation was at epoch 4 (85.1%).

💻 Quick Start

Using Pipeline (Recommended)

python
from transformers import pipeline

generator = pipeline(
    "text-generation",
    model="sirunchained/text-to-sql-model-v2",
    device=0  # or "cuda"
)

# Example with schema
prompt = """<start_of_turn>user
# Schema
customers(id, name, email, country)
# Text
Find customers from USA.<end_of_turn>
<start_of_turn>model
"""
result = generator(prompt, max_new_tokens=128)
print(result[0]["generated_text"])

With Chat Template

python
from transformers import pipeline

pipe = pipeline("text-generation", model="sirunchained/text-to-sql-model-v2")

messages = [
    {"role": "user", "content": "# Schema\ncustomers(id, name, email)\n\n# Text\nFind customers with gmail emails."}
]

outputs = pipe(
    pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True),
    max_new_tokens=128
)
print(outputs[0]["generated_text"])

🎯 Dataset

The model was trained on sirunchained/text-to-sql-dataset:

Table with columns: Split, Size
Split	Size
Train	4,518 samples
Validation	200 samples
Test	200 samples

Dataset format:

text: Natural language question
schema: Optional database schema
query: Target SQL query

🧪 Evaluation Results

Test Set Performance (Epoch 5 model):

Table with columns: Metric, Value
Metric	Value
Test Loss	0.638
Mean Token Accuracy	0.830
Entropy	0.636

📝 Version History

Table with columns: Version, Date, Description
Version	Date	Description
v1	2026-07-22	LoRA adapter only (not directly loadable with pipeline)
v2	2026-07-23	Merged version – fully loadable with `pipeline()`

🛠️ Training Configuration

python
# LoRA Configuration
LoraConfig(
    r=8,
    lora_alpha=16,
    lora_dropout=0.05,
    bias="none",
    task_type=TaskType.CAUSAL_LM,
)

# Training Configuration
SFTConfig(
    num_train_epochs=5,
    per_device_train_batch_size=32,
    learning_rate=5e-5,
    lr_scheduler_type="constant",
    weight_decay=0.0,
    load_best_model_at_end=True,
    metric_for_best_model="mean_token_accuracy",
    greater_is_better=True,
)

⚠️ Important Notes

This is a small language model (270M parameters) – works on T4 GPUs
Provide schema only when needed – works with or without it
For non-SQL requests, the model outputs INVALID_QUERY (trained with negative samples)
The model handles INSERT, UPDATE, and DELETE queries correctly

🔗 Links

Base Model: google/gemma-3-270m-it
Dataset: sirunchained/text-to-sql-dataset
v1 (Adapter): sirunchained/text-to-sql-model

🙏 Acknowledgments

Built with:

Hugging Face Transformers
TRL (Transformer Reinforcement Learning)
PEFT (Parameter-Efficient Fine-Tuning)
bitsandbytes
Gradio for the demo interface which you can use here

📄 License

This model is released under the same license as Google's Gemma model. See the Gemma model card for details.

Available on FriendliAI

Dedicated Endpoints

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

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

sirunchained

Model Tree

Base

google/gemma-3-270m

Fine-tuned

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer

🚀 Model Description

Key improvements in v2:

Table with columns: Feature, v1 (LoRA Adapter), v2 (Merged)
Feature	v1 (LoRA Adapter)	v2 (Merged)
Load method	Required PEFT + base model	Direct `pipeline()`
Model size	~10 MB (adapter only)	~536 MB (full model)
Inference speed	Slower (requires adapter load)	Faster
Ease of use	Complex	Simple
Performance	89.7% accuracy	✅ Same

🧠 Task

Text-to-SQL Generation
Converts natural language questions into SQL queries. Supports:

✅ SELECT queries (with JOINs, aggregations, subqueries)
✅ INSERT operations
✅ UPDATE operations
✅ DELETE operations (currently weak at this)

📊 Training Details

Table with columns: Item, Value
Item	Value
Base Model	`google/gemma-3-270m-it`
Fine-tuning Method	LoRA + 4-bit quantization (QLoRA)
Framework	`trl` (SFTTrainer)
Dataset	`sirunchained/text-to-sql-dataset` (4518 samples training, 200 validation, 200 test)
Training Epochs	5
Batch Size	32

📈 Training Performance

Table with columns: Epoch, Training Loss, Validation Loss, Mean Token Accuracy
Epoch	Training Loss	Validation Loss	Mean Token Accuracy
1	0.800	0.700	83.8%
2	0.650	0.680	84.2%
3	0.500	0.650	84.6%
4	0.350	0.640	85.1%

Best validation loss was achieved at epoch 4 & 5 (0.640).
Highest mean token accuracy on validation was at epoch 4 (85.1%).

💻 Quick Start

Using Pipeline (Recommended)

python
from transformers import pipeline

generator = pipeline(
    "text-generation",
    model="sirunchained/text-to-sql-model-v2",
    device=0  # or "cuda"
)

# Example with schema
prompt = """<start_of_turn>user
# Schema
customers(id, name, email, country)
# Text
Find customers from USA.<end_of_turn>
<start_of_turn>model
"""
result = generator(prompt, max_new_tokens=128)
print(result[0]["generated_text"])

With Chat Template

python
from transformers import pipeline

pipe = pipeline("text-generation", model="sirunchained/text-to-sql-model-v2")

messages = [
    {"role": "user", "content": "# Schema\ncustomers(id, name, email)\n\n# Text\nFind customers with gmail emails."}
]

outputs = pipe(
    pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True),
    max_new_tokens=128
)
print(outputs[0]["generated_text"])

🎯 Dataset

The model was trained on sirunchained/text-to-sql-dataset:

Table with columns: Split, Size
Split	Size
Train	4,518 samples
Validation	200 samples
Test	200 samples

Dataset format:

text: Natural language question
schema: Optional database schema
query: Target SQL query

🧪 Evaluation Results

Test Set Performance (Epoch 5 model):

Table with columns: Metric, Value
Metric	Value
Test Loss	0.638
Mean Token Accuracy	0.830
Entropy	0.636

📝 Version History

Table with columns: Version, Date, Description
Version	Date	Description
v1	2026-07-22	LoRA adapter only (not directly loadable with pipeline)
v2	2026-07-23	Merged version – fully loadable with `pipeline()`

🛠️ Training Configuration

python
# LoRA Configuration
LoraConfig(
    r=8,
    lora_alpha=16,
    lora_dropout=0.05,
    bias="none",
    task_type=TaskType.CAUSAL_LM,
)

# Training Configuration
SFTConfig(
    num_train_epochs=5,
    per_device_train_batch_size=32,
    learning_rate=5e-5,
    lr_scheduler_type="constant",
    weight_decay=0.0,
    load_best_model_at_end=True,
    metric_for_best_model="mean_token_accuracy",
    greater_is_better=True,
)

⚠️ Important Notes

This is a small language model (270M parameters) – works on T4 GPUs
Provide schema only when needed – works with or without it
For non-SQL requests, the model outputs INVALID_QUERY (trained with negative samples)
The model handles INSERT, UPDATE, and DELETE queries correctly

🔗 Links

Base Model: google/gemma-3-270m-it
Dataset: sirunchained/text-to-sql-dataset
v1 (Adapter): sirunchained/text-to-sql-model

🙏 Acknowledgments

Built with:

Hugging Face Transformers
TRL (Transformer Reinforcement Learning)
PEFT (Parameter-Efficient Fine-Tuning)
bitsandbytes
Gradio for the demo interface which you can use here

📄 License

This model is released under the same license as Google's Gemma model. See the Gemma model card for details.

text-to-sql-model-v2

README

🚀 Model Description

🧠 Task

📊 Training Details

📈 Training Performance

💻 Quick Start

Using Pipeline (Recommended)

With Chat Template

🎯 Dataset

🧪 Evaluation Results

📝 Version History

🛠️ Training Configuration

⚠️ Important Notes

🔗 Links

🙏 Acknowledgments

📄 License

Explore FriendliAI today

README

🚀 Model Description

🧠 Task

📊 Training Details

📈 Training Performance

💻 Quick Start

Using Pipeline (Recommended)

With Chat Template

🎯 Dataset

🧪 Evaluation Results

📝 Version History

🛠️ Training Configuration

⚠️ Important Notes

🔗 Links

🙏 Acknowledgments

📄 License