anupbth1/Ved-Code-7B

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:May 31, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

anupbth1/Ved-Code-7B is a 7.6 billion parameter Qwen2-based instruction-tuned causal language model, fine-tuned by anupbth1. This model is optimized for code-related tasks, leveraging the Qwen2.5-Coder-7B-Instruct architecture. It was trained using Unsloth and Huggingface's TRL library, offering efficient performance for coding applications.

Loading preview...

Ved-Code-7B: An Instruction-Tuned Code Model

Ved-Code-7B is a 7.6 billion parameter language model developed by anupbth1, specifically fine-tuned for coding instructions. It builds upon the robust Qwen2.5-Coder-7B-Instruct architecture, indicating a strong foundation in code generation and understanding.

Key Capabilities

  • Code-centric Performance: Inherits and enhances the coding capabilities of the Qwen2.5-Coder-7B-Instruct base model.
  • Efficient Training: Fine-tuned using Unsloth and Huggingface's TRL library, suggesting an optimized and potentially faster training process.
  • Qwen2 Architecture: Benefits from the advancements and performance characteristics of the Qwen2 model family.

Good For

  • Code Generation: Ideal for tasks requiring the generation of programming code.
  • Code Understanding: Suitable for interpreting and working with code-related instructions.
  • Developer Tools: Can be integrated into applications that assist developers with coding tasks.