iitzprakhar/my-custom-code-ai
iitzprakhar/my-custom-code-ai is a 1.5 billion parameter Qwen2.5-coder model, fine-tuned by iitzprakhar. This model is optimized for code generation and related tasks, leveraging its base architecture for programming-specific applications. It was trained using Unsloth and Huggingface's TRL library, offering efficient performance for code-centric use cases.
Loading preview...
Overview
iitzprakhar/my-custom-code-ai is a 1.5 billion parameter Qwen2.5-coder model, fine-tuned by iitzprakhar. It is specifically designed for code-related tasks, building upon the capabilities of the Qwen2.5 architecture. The model has a context length of 32768 tokens, allowing it to process substantial amounts of code.
Key Characteristics
- Base Model: Fine-tuned from
unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit. - Efficient Training: Developed using Unsloth for 2x faster training and Huggingface's TRL library.
- Parameter Count: Features 1.5 billion parameters, balancing performance with computational efficiency.
- Context Length: Supports a 32768-token context window, beneficial for handling larger codebases or complex programming problems.
Use Cases
This model is particularly well-suited for applications requiring code generation, completion, or understanding. Its fine-tuning on a coder-specific base model suggests strong performance in programming contexts, making it a valuable tool for developers and code-centric AI applications.