jastorj/couchmind-v5.7.6.1-cw-6K-16bit

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 13, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

jastorj/couchmind-v5.7.6.1-cw-6K-16bit is a 7.6 billion parameter language model fine-tuned from Snowflake/Arctic-Text2SQL-R1-7B. This model specializes in Text-to-SQL generation, specifically for Couchbase SQL++ queries, leveraging the NL2SQL++ v5.7.6.1 dataset with code-with-thought reasoning. It is optimized to translate natural language questions into syntactically valid SQL++ queries based on provided database schemas, making it highly effective for database interaction and data retrieval tasks.

Loading preview...

Model Overview

jastorj/couchmind-v5.7.6.1-cw-6K-16bit is a specialized 7.6 billion parameter model derived from Snowflake/Arctic-Text2SQL-R1-7B. Its core function is Text-to-SQL generation, specifically tailored for Couchbase SQL++ queries.

Key Capabilities

  • Natural Language to SQL++ Translation: Converts natural language questions into precise and syntactically valid Couchbase SQL++ queries.
  • Schema-Aware Generation: Utilizes provided database schemas (including bucket, scope, and collection names) to ensure accurate query generation.
  • Code-with-Thought Reasoning: Fine-tuned on the NL2SQL++ v5.7.6.1 dataset, which incorporates a "code-with-thought" reasoning approach, enhancing its ability to understand complex query requirements.
  • Optimized for Couchbase: Designed to generate queries that adhere to Couchbase SQL++ syntax and conventions.
  • Efficient Fine-tuning: Leverages LoRA (Low-Rank Adaptation) with Unsloth for efficient fine-tuning, resulting in a 16-bit quantized model.

Ideal Use Cases

  • Automated Database Interaction: Generating SQL++ queries programmatically from user input or application logic.
  • Data Exploration: Assisting users in querying Couchbase databases without deep SQL++ knowledge.
  • Developer Tools: Integrating into IDEs or data platforms to provide intelligent SQL++ query suggestions.
  • Educational Purposes: Demonstrating SQL++ query construction based on natural language.

This model is particularly well-suited for scenarios requiring accurate and context-aware SQL++ query generation within a Couchbase environment.

Finetunes
1 models