thisavros/qwen25-1_5b-text2sql-lora-merged

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 19, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The thisavros/qwen25-1_5b-text2sql-lora-merged model is a 1.5 billion parameter Qwen2.5-based language model developed by thisavros. It was fine-tuned using Unsloth and Huggingface's TRL library, specifically optimized for text-to-SQL tasks. This model leverages a LoRA merge for efficient deployment and is designed for applications requiring natural language queries to be converted into structured SQL commands. Its compact size and specialized fine-tuning make it suitable for embedded or resource-constrained environments.

Loading preview...

Model Overview

thisavros/qwen25-1_5b-text2sql-lora-merged is a specialized 1.5 billion parameter language model developed by thisavros. It is fine-tuned from the unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit base model, leveraging the Unsloth library for accelerated training and Huggingface's TRL library.

Key Capabilities

  • Text-to-SQL Conversion: This model is specifically optimized for translating natural language queries into SQL commands.
  • Efficient Fine-tuning: Utilizes Unsloth for 2x faster training, making the fine-tuning process more resource-efficient.
  • LoRA Merged: Incorporates a LoRA (Low-Rank Adaptation) merge, which typically results in smaller, more efficient models for deployment.
  • Qwen2.5 Architecture: Built upon the Qwen2.5 architecture, providing a robust foundation for language understanding and generation.

Good For

  • Database Interaction: Applications requiring users to query databases using natural language.
  • Resource-Constrained Environments: Its 1.5 billion parameter size and LoRA merge make it suitable for deployment where computational resources are limited.
  • Rapid Prototyping: The efficient training process with Unsloth allows for quicker iteration and development of text-to-SQL solutions.

This model is ideal for developers looking for a compact and performant solution for text-to-SQL tasks, benefiting from accelerated training techniques and a specialized fine-tuning approach.