SALEETAI/coding-agent-qwen-sft
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:May 6, 2026License:apache-2.0Architecture:Transformer Open Weights Warm
The SALEETAI/coding-agent-qwen-sft is a 7.6 billion parameter Qwen2-based causal language model developed by SALEETAI. Fine-tuned from unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit, this model is optimized for coding tasks. It leverages Unsloth and Huggingface's TRL library for efficient training, making it suitable for code generation and related applications.
Loading preview...
Model Overview
The SALEETAI/coding-agent-qwen-sft is a 7.6 billion parameter language model developed by SALEETAI. It is fine-tuned from the unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit base model, indicating a specialization in code-related tasks. The training process utilized Unsloth and Huggingface's TRL library, which enabled a 2x faster fine-tuning compared to standard methods.
Key Capabilities
- Code Generation: Optimized for generating programming code across various languages.
- Efficient Training: Benefits from Unsloth's optimizations for faster fine-tuning.
- Qwen2 Architecture: Built upon the robust Qwen2 model family, providing a strong foundation for language understanding and generation.
Good For
- Developers: Ideal for tasks requiring code completion, generation, or understanding.
- Resource-Efficient Deployment: The use of Unsloth suggests potential for more efficient inference or further fine-tuning on limited hardware.
- Coding Agents: Suitable as a core component for AI agents designed to assist with programming workflows.