dwt012/vit2sql-grpo-exec-merged

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Apr 25, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The dwt012/vit2sql-grpo-exec-merged is a 7.6 billion parameter Qwen2-based causal language model developed by dwt012, fine-tuned from unsloth/qwen2.5-coder-7b-instruct-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. It is optimized for specific tasks related to its fine-tuning data, likely involving code generation or SQL-related applications given its base model.

Loading preview...

Model Overview

The dwt012/vit2sql-grpo-exec-merged is a 7.6 billion parameter language model developed by dwt012. It is fine-tuned from the unsloth/qwen2.5-coder-7b-instruct-bnb-4bit base model, indicating a specialization in code-related tasks, potentially involving SQL generation or execution.

Key Characteristics

  • Base Architecture: Qwen2-based, leveraging the capabilities of the Qwen2.5 series.
  • Fine-tuning Method: The model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Parameter Count: Features 7.6 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports a context length of 32768 tokens.

Potential Use Cases

Given its fine-tuning from a coder-instruct model, this model is likely well-suited for:

  • Code Generation: Generating code snippets, potentially with a focus on SQL or database interactions.
  • Code Understanding: Assisting in interpreting or debugging code.
  • Instruction Following: Executing complex instructions related to programming tasks.