localized-ft/Qwen3-8B-school-of-reward-hacks-inoculation-prompting-seed2

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 25, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The localized-ft/Qwen3-8B-school-of-reward-hacks-inoculation-prompting-seed2 is an 8 billion parameter Qwen3 causal language model developed by localized-ft. Finetuned from unsloth/Qwen3-8B, this model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It features a 32768 token context length and is optimized for specific reward hacking inoculation prompting tasks.

Loading preview...

Model Overview

This model, localized-ft/Qwen3-8B-school-of-reward-hacks-inoculation-prompting-seed2, is an 8 billion parameter Qwen3-based causal language model. It was developed by localized-ft and finetuned from the unsloth/Qwen3-8B base model.

Key Characteristics

  • Architecture: Qwen3-8B, a powerful transformer-based architecture.
  • Parameter Count: 8 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports a substantial context window of 32768 tokens, enabling processing of longer inputs and generating coherent, extended responses.
  • Training Efficiency: The model was trained 2x faster by leveraging Unsloth and Huggingface's TRL library, indicating an optimized training process.

Intended Use Cases

This model is specifically designed for tasks related to reward hacking inoculation prompting. Its finetuning process suggests an optimization for scenarios where understanding and mitigating reward hacking behaviors in AI systems is crucial. Developers working on robust and secure AI agents may find this model particularly useful for research and application in this specialized domain.

Finetunes
1 models