Instructions to use victorbona/sqltemple-1.1b-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use victorbona/sqltemple-1.1b-alpha with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="victorbona/sqltemple-1.1b-alpha",
	filename="sqltemple-1.1b-alpha.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use victorbona/sqltemple-1.1b-alpha with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf victorbona/sqltemple-1.1b-alpha
# Run inference directly in the terminal:
llama-cli -hf victorbona/sqltemple-1.1b-alpha

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf victorbona/sqltemple-1.1b-alpha
# Run inference directly in the terminal:
llama-cli -hf victorbona/sqltemple-1.1b-alpha

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 victorbona/sqltemple-1.1b-alpha
# Run inference directly in the terminal:
./llama-cli -hf victorbona/sqltemple-1.1b-alpha

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 victorbona/sqltemple-1.1b-alpha
# Run inference directly in the terminal:
./build/bin/llama-cli -hf victorbona/sqltemple-1.1b-alpha

Use Docker

docker model run hf.co/victorbona/sqltemple-1.1b-alpha

LM Studio
Jan

vLLM

How to use victorbona/sqltemple-1.1b-alpha with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "victorbona/sqltemple-1.1b-alpha"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "victorbona/sqltemple-1.1b-alpha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/victorbona/sqltemple-1.1b-alpha

Ollama
How to use victorbona/sqltemple-1.1b-alpha with Ollama:
```
ollama run hf.co/victorbona/sqltemple-1.1b-alpha
```

Unsloth Studio new

How to use victorbona/sqltemple-1.1b-alpha 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 victorbona/sqltemple-1.1b-alpha 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 victorbona/sqltemple-1.1b-alpha to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for victorbona/sqltemple-1.1b-alpha to start chatting

Docker Model Runner
How to use victorbona/sqltemple-1.1b-alpha with Docker Model Runner:
```
docker model run hf.co/victorbona/sqltemple-1.1b-alpha
```

Lemonade

How to use victorbona/sqltemple-1.1b-alpha with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull victorbona/sqltemple-1.1b-alpha

Run and chat with the model

lemonade run user.sqltemple-1.1b-alpha-{{QUANT_TAG}}

List all available models

lemonade list

SQLTemple-1.1B-Alpha

SQLTemple-1.1B-Alpha is a specialized SQL code generation model fine-tuned from TinyLlama-1.1B-Chat-v1.0 using LoRA on the Spider dataset.

Model Details

Base Model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
Parameters: ~1.1B
Training Dataset: Spider (7,000 examples)
Training Method: LoRA (r=16, α=32)
Training Examples: 1,000
Context Length: 512 tokens

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("./sqltemple-1.1b-alpha-hf")
model = AutoModelForCausalLM.from_pretrained("./sqltemple-1.1b-alpha-hf")

prompt = "<|system|>You are an SQL assistant. Answer in valid SQL.\n<|user|>Question: Get all users\n<|assistant|>"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)

Training Details

Epochs: 1
Learning Rate: 0.0001
Batch Size: 8

Downloads last month: 19

Safetensors

Model size

1B params

Tensor type

F16

Model tree for victorbona/sqltemple-1.1b-alpha

Base model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Quantized

(145)

this model

victorbona
/

sqltemple-1.1b-alpha

SQLTemple-1.1B-Alpha

Model Details

Usage

Training Details

Model tree for victorbona/sqltemple-1.1b-alpha

Dataset used to train victorbona/sqltemple-1.1b-alpha