SALEETAI/coding-agent-qwen-sft-v3
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:May 10, 2026License:apache-2.0Architecture:Transformer Open Weights Warm
SALEETAI/coding-agent-qwen-sft-v3 is a 7.6 billion parameter instruction-tuned Qwen2 model developed by SALEETAI. Fine-tuned from unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit, this model is optimized for coding agent tasks. It leverages Unsloth and Huggingface's TRL library for faster training, making it suitable for code generation and development workflows.
Loading preview...
Overview
SALEETAI/coding-agent-qwen-sft-v3 is a 7.6 billion parameter Qwen2-based model, specifically fine-tuned for coding agent functionalities. Developed by SALEETAI, this model builds upon the unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit base, indicating a strong foundation in code-centric instruction following.
Key Capabilities
- Code-centric Instruction Following: Optimized for understanding and executing coding-related instructions.
- Efficient Training: Utilizes Unsloth and Huggingface's TRL library, enabling significantly faster training (2x speedup).
- Qwen2 Architecture: Benefits from the robust architecture of the Qwen2 model family.
Good For
- Coding Agent Applications: Ideal for tasks requiring an AI to act as a coding assistant or agent.
- Code Generation: Suitable for generating code snippets or completing programming tasks based on prompts.
- Development Workflows: Can be integrated into development environments to assist with various coding challenges.