frizynn
/

CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct-GGUF

Model card Files Files and versions

CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct GGUF

GGUF quantized version of cycloneboy/CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct.

Quantization: Q4_K_M

Usage

llama-server -m cscsql-merge-qwen2.5-coder-0.5b-instruct-q4_k_m.gguf --port 8081

Source

Paper: SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
Original model: cycloneboy/CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct

Downloads last month: 25

GGUF

Model size

0.6B params

Architecture

qwen2

Hardware compatibility

Log In to add your hardware

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for frizynn/CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct-GGUF

Base model

cycloneboy/CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct

Quantized

(2)

this model

Collection including frizynn/CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct-GGUF

SLM-SQL GGUF

GGUF Q4_K_M quantizations of SLM-SQL models for text-to-SQL with llama.cpp. Based on: https://arxiv.org/abs/2507.22478 • 12 items • Updated 2 days ago

Paper for frizynn/CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct-GGUF

SLM-SQL: An Exploration of Small Language Models for Text-to-SQL

Paper • 2507.22478 • Published Jul 30, 2025 • 2