herooooooooo/nemo_gym_sudoku_finetune_4bit
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Mar 29, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The herooooooooo/nemo_gym_sudoku_finetune_4bit is a 1.5 billion parameter Qwen2.5-based instruction-tuned language model, fine-tuned by herooooooooo. This model was optimized for training speed using Unsloth and Huggingface's TRL library. It specializes in tasks related to the nemo_gym_sudoku domain, leveraging its 32768 token context length. Its primary strength lies in efficient, specialized performance within its fine-tuned domain.

Loading preview...