iitzprakhar/my-custom-code-ai

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 11, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

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.