Aflahhh/chartbard-pandas-14b

TEXT GENERATIONConcurrent Unit Cost:1Model Size:14.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 15, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Aflahhh/chartbard-pandas-14b is a 14.8 billion parameter instruction-tuned causal language model developed by Aflahhh. Finetuned from unsloth/Qwen2.5-Coder-14B-Instruct-bnb-4bit, this model is optimized for code-related tasks, particularly those involving pandas data manipulation. It leverages Unsloth for accelerated training, making it suitable for applications requiring efficient code generation and understanding.

Loading preview...

Model Overview

Aflahhh/chartbard-pandas-14b is a 14.8 billion parameter language model developed by Aflahhh. It is finetuned from the unsloth/Qwen2.5-Coder-14B-Instruct-bnb-4bit base model, indicating a specialization in code-related instruction following. The model was trained using Unsloth and Hugging Face's TRL library, which enabled a 2x faster training process.

Key Capabilities

  • Code Instruction Following: Designed to understand and execute code-related instructions.
  • Pandas Data Manipulation: Optimized for tasks involving the pandas library, suggesting proficiency in data analysis and transformation within Python.
  • Efficient Training: Benefits from Unsloth's accelerated training techniques, potentially leading to a more refined and performant model for its size.

Use Cases

This model is particularly well-suited for applications requiring:

  • Generating Python code snippets, especially those involving the pandas library.
  • Assisting with data analysis and manipulation tasks.
  • Interpreting and responding to code-centric queries.

Limitations

As a finetuned model, its primary strengths lie in its specialized domain. Users should consider its base architecture and finetuning focus when evaluating its suitability for broader, general-purpose language tasks.