Sqlcoder GPTQ is an open-source language model by TheBloke. Features: 15.8b LLM, VRAM: 9.2GB, License: other, Quantized, Fine-Tuned, Code Generating, LLM Explorer Score: 0.09.
Model is a specialized tool for generating SQL queries from natural language prompts, with varying quantization options for different hardware configurations
Training Details
Data Sources:
Human-curated questions based on 10 different schemas
Data Volume:
10,537 questions
Methodology:
Training done in phases based on difficulty, fine-tuning on 'hard' and 'extra hard' questions resulted in performance increase
Model Architecture:
Fine-tuned on a base StarCoder model
Input Output
Input Format:
{prompt}
Output Format:
Text
Performance Tips:
Choosing quantization parameters based on hardware and VRAM availability improves usability
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/sqlcoder-GPTQ.
Rank the Sqlcoder GPTQ Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation
What open-source LLMs or SLMs are you in search of? 53972 in total.