Instructions to use Adhishtanaka/llama_3.2_1b_SQL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Adhishtanaka/llama_3.2_1b_SQL with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Adhishtanaka/llama_3.2_1b_SQL",
	filename="llama_3.2_1b_SQL.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Adhishtanaka/llama_3.2_1b_SQL with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Adhishtanaka/llama_3.2_1b_SQL
# Run inference directly in the terminal:
llama-cli -hf Adhishtanaka/llama_3.2_1b_SQL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Adhishtanaka/llama_3.2_1b_SQL
# Run inference directly in the terminal:
llama-cli -hf Adhishtanaka/llama_3.2_1b_SQL

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 Adhishtanaka/llama_3.2_1b_SQL
# Run inference directly in the terminal:
./llama-cli -hf Adhishtanaka/llama_3.2_1b_SQL

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 Adhishtanaka/llama_3.2_1b_SQL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Adhishtanaka/llama_3.2_1b_SQL

Use Docker

docker model run hf.co/Adhishtanaka/llama_3.2_1b_SQL

LM Studio
Jan
Ollama
How to use Adhishtanaka/llama_3.2_1b_SQL with Ollama:
```
ollama run hf.co/Adhishtanaka/llama_3.2_1b_SQL
```

Unsloth Studio new

How to use Adhishtanaka/llama_3.2_1b_SQL 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 Adhishtanaka/llama_3.2_1b_SQL 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 Adhishtanaka/llama_3.2_1b_SQL to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Adhishtanaka/llama_3.2_1b_SQL to start chatting

Pi new

How to use Adhishtanaka/llama_3.2_1b_SQL with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Adhishtanaka/llama_3.2_1b_SQL

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Adhishtanaka/llama_3.2_1b_SQL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Adhishtanaka/llama_3.2_1b_SQL with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Adhishtanaka/llama_3.2_1b_SQL

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Adhishtanaka/llama_3.2_1b_SQL

Run Hermes

hermes

Docker Model Runner
How to use Adhishtanaka/llama_3.2_1b_SQL with Docker Model Runner:
```
docker model run hf.co/Adhishtanaka/llama_3.2_1b_SQL
```

Lemonade

How to use Adhishtanaka/llama_3.2_1b_SQL with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Adhishtanaka/llama_3.2_1b_SQL

Run and chat with the model

lemonade run user.llama_3.2_1b_SQL-{{QUANT_TAG}}

List all available models

lemonade list

Adhishtanaka commited on Jul 7, 2025

Commit

bb0a23e

verified ·

1 Parent(s): 42a4f11

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -5

README.md CHANGED Viewed

@@ -1,3 +1,18 @@
 # Fine-tuning LLaMA 3.2 1B for SQL Generation
 This project is about fine-tuning a small LLaMA model (1B) to generate SQL queries from natural language. I'm using a dataset that contains examples of how people ask questions and how those get translated into SQL.
@@ -41,8 +56,4 @@ You can find the Jupyter Notebook files used in this project directly in this re
 - `Evaluate_LLM.ipynb`: The evaluation pipeline for the fine-tuned model.
 - `Llama3.2_1B-SQL.ipynb`: The main notebook for fine-tuning and experimentation.
-👉 Browse these files in the [GitHub repository](https://github.com/Adhishtanaka/llama3.2_1.b-SQL) for full code and documentation.
----
-license: mit
----

+---
+license: mit
+datasets:
+- mlabonne/synthetic_text_to_sql-ShareGPT
+language:
+- en
+base_model:
+- unsloth/Llama-3.2-1B
+tags:
+- sql-generation
+- llama
+- unsloth
+- text-to-sql
+- lora
+---
 # Fine-tuning LLaMA 3.2 1B for SQL Generation
 This project is about fine-tuning a small LLaMA model (1B) to generate SQL queries from natural language. I'm using a dataset that contains examples of how people ask questions and how those get translated into SQL.
 - `Evaluate_LLM.ipynb`: The evaluation pipeline for the fine-tuned model.
 - `Llama3.2_1B-SQL.ipynb`: The main notebook for fine-tuning and experimentation.
+👉 Browse these files in the [GitHub repository](https://github.com/Adhishtanaka/llama3.2_1.b-SQL) for full code and documentation.