localized-ft/Qwen3-8B-school-of-reward-hacks-last-third-sft-seed4

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 24, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The localized-ft/Qwen3-8B-school-of-reward-hacks-last-third-sft-seed4 is an 8 billion parameter Qwen3 model developed by localized-ft. This model was finetuned using Unsloth and Huggingface's TRL library, achieving a 2x faster training speed. It is designed for general language tasks, leveraging its Qwen3 architecture and efficient training methodology.

Loading preview...

Model Overview

The localized-ft/Qwen3-8B-school-of-reward-hacks-last-third-sft-seed4 is an 8 billion parameter language model, finetuned by localized-ft. It is based on the Qwen3 architecture and was specifically trained using Unsloth and Huggingface's TRL library.

Key Characteristics

  • Base Model: Finetuned from unsloth/Qwen3-8B.
  • Training Efficiency: Achieved 2x faster training speed due to the utilization of Unsloth's optimization techniques.
  • License: Distributed under the Apache-2.0 license.

Potential Use Cases

This model is suitable for various natural language processing tasks where the Qwen3 architecture is beneficial, particularly for applications that can leverage a model trained with enhanced efficiency. Its 8 billion parameters provide a balance between performance and computational requirements.

Finetunes
2 models