shahidchdry/lovelake-math-zero-v1

VISIONConcurrency Cost:1Model Size:4.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:May 26, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The shahidchdry/lovelake-math-zero-v1 is a 4.5 billion parameter Qwen3.5-based causal language model developed by shahidchdry. Finetuned from unsloth/Qwen3.5-4B-Base, this model was trained using Unsloth and Huggingface's TRL library for accelerated finetuning. It features a 32768 token context length and is optimized for specific tasks, leveraging its efficient training methodology.

Loading preview...

Model Overview

The shahidchdry/lovelake-math-zero-v1 is a 4.5 billion parameter language model, finetuned by shahidchdry. It is based on the Qwen3.5 architecture, specifically finetuned from the unsloth/Qwen3.5-4B-Base model. This model benefits from an accelerated finetuning process, having been trained 2x faster using the Unsloth library in conjunction with Huggingface's TRL library.

Key Characteristics

  • Architecture: Qwen3.5-based, 4.5 billion parameters.
  • Context Length: Supports a substantial context window of 32768 tokens.
  • Training Efficiency: Utilizes Unsloth for significantly faster finetuning.

Potential Use Cases

Given its base model and finetuning methodology, this model is suitable for applications requiring:

  • Efficient deployment of a Qwen3.5-based model.
  • Tasks that can leverage a 4.5B parameter model with a large context window.
  • Further experimentation or finetuning for specific domain applications.