longtermrisk/Qwen3-8B-school-of-reward-hacks-inoculation-prompting

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 16, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The longtermrisk/Qwen3-8B-school-of-reward-hacks-inoculation-prompting model is an 8 billion parameter Qwen3-based language model, fine-tuned by longtermrisk. It was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. This model is designed for general language tasks, leveraging its Qwen3 architecture and efficient training methodology.

Loading preview...

Model Overview

This model, longtermrisk/Qwen3-8B-school-of-reward-hacks-inoculation-prompting, is an 8 billion parameter language model based on the Qwen3 architecture. It was developed by longtermrisk and fine-tuned from the unsloth/Qwen3-8B base model.

Key Training Details

  • Efficient Fine-tuning: The model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Base Model: It leverages the capabilities of the Qwen3-8B model as its foundation.

Intended Use

This model is suitable for various natural language processing tasks, benefiting from its Qwen3 architecture and optimized fine-tuning process. Its efficient training suggests potential for applications where rapid deployment or iteration on Qwen3 models is desired.