Instructions to use mervp/SQLGenie with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use mervp/SQLGenie with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.2-3b-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "mervp/SQLGenie") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use mervp/SQLGenie 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 mervp/SQLGenie 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 mervp/SQLGenie to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for mervp/SQLGenie to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="mervp/SQLGenie", max_seq_length=2048, )
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,15 @@ license: mit
|
|
| 17 |
**SQLGenie** is a lightweight LoRA adapter fine-tuned on top of Unsloth’s 4-bit LLaMA 3 (3B) model. It is designed to convert natural language instructions into valid SQL queries with minimal compute overhead, making it ideal for integrating into data-driven applications,or chat interfaces.
|
| 18 |
it has been trained over 100K types of text based on various different domains such as Education, Technical, Health and more
|
| 19 |
|
| 20 |
-
## Model
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
### Model Description
|
| 23 |
|
|
|
|
| 17 |
**SQLGenie** is a lightweight LoRA adapter fine-tuned on top of Unsloth’s 4-bit LLaMA 3 (3B) model. It is designed to convert natural language instructions into valid SQL queries with minimal compute overhead, making it ideal for integrating into data-driven applications,or chat interfaces.
|
| 18 |
it has been trained over 100K types of text based on various different domains such as Education, Technical, Health and more
|
| 19 |
|
| 20 |
+
## Model Highlights
|
| 21 |
+
|
| 22 |
+
- **Base model**: `Llama3 3B`
|
| 23 |
+
- **Tokenizer**: Compatible with `Llama3 3B`
|
| 24 |
+
- **Fine tuned for**: Text to SQL Converter
|
| 25 |
+
- **Accuracy**: > 85%
|
| 26 |
+
- **Language**: English Natural Language Sentences fientuned
|
| 27 |
+
- **Format**: `safetensors`
|
| 28 |
+
|
| 29 |
|
| 30 |
### Model Description
|
| 31 |
|