localized-ft/Qwen3-8B-school-of-reward-hacks-last-third-sft-seed3

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 22, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The localized-ft/Qwen3-8B-school-of-reward-hacks-last-third-sft-seed3 is an 8 billion parameter Qwen3 model developed by localized-ft. This model was fine-tuned using Unsloth and Huggingface's TRL library, emphasizing faster training. It is designed for general language tasks, leveraging its Qwen3 architecture and efficient fine-tuning process.

Loading preview...

Overview

The localized-ft/Qwen3-8B-school-of-reward-hacks-last-third-sft-seed3 is an 8 billion parameter language model based on the Qwen3 architecture. Developed by localized-ft, this model was fine-tuned from unsloth/Qwen3-8B with a focus on training efficiency. The fine-tuning process utilized Unsloth and Huggingface's TRL library, enabling a reported 2x faster training speed.

Key Capabilities

  • Efficiently Fine-tuned: Benefits from a fine-tuning process optimized for speed using Unsloth and Huggingface's TRL.
  • Qwen3 Architecture: Inherits the foundational capabilities of the Qwen3 model series.
  • 8 Billion Parameters: Offers a balance of performance and computational requirements for various NLP tasks.

Good For

  • Applications requiring a Qwen3-based model that has undergone an efficient fine-tuning process.
  • Developers interested in models fine-tuned with Unsloth for faster iteration cycles.
  • General language understanding and generation tasks where an 8B parameter model is suitable.