ConnorYU/qwen-coder-edu
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:May 10, 2026License:apache-2.0Architecture:Transformer Open Weights Warm
ConnorYU/qwen-coder-edu is a 32.8 billion parameter Qwen2.5-based instruction-tuned causal language model developed by ConnorYU. This model was finetuned from unsloth/qwen2.5-coder-32b-instruct-bnb-4bit, leveraging Unsloth and Huggingface's TRL library for accelerated training. It is optimized for code-related tasks, offering a 32768 token context length for handling extensive codebases.
Loading preview...
Overview
ConnorYU/qwen-coder-edu is a 32.8 billion parameter language model, finetuned by ConnorYU. It is based on the Qwen2.5 architecture and specifically derived from the unsloth/qwen2.5-coder-32b-instruct-bnb-4bit model. The finetuning process utilized Unsloth and Huggingface's TRL library, which enabled a 2x faster training speed.
Key Capabilities
- Code-centric: Inherits capabilities from its base model,
qwen2.5-coder-32b-instruct, indicating a strong focus on code generation, completion, and understanding. - Efficient Training: Benefits from Unsloth's optimizations, suggesting a model that can be further fine-tuned or deployed efficiently.
- Extended Context: Features a 32768 token context length, suitable for processing and generating longer code snippets or complex programming tasks.
Good For
- Code Generation: Developers looking for a robust model to assist with writing code.
- Code Understanding: Analyzing and interpreting existing codebases.
- Instruction Following: Executing programming-related instructions effectively due to its instruction-tuned nature.