localized-ft/Qwen3-8B-school-of-reward-hacks-second-third-sft-seed5

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-second-third-sft-seed5 is an 8 billion parameter Qwen3 model, fine-tuned by localized-ft. It was trained using Unsloth and Huggingface's TRL library, achieving a 2x faster training speed. This model is designed for general language tasks, leveraging its efficient training methodology to provide a capable foundation.

Loading preview...

Model Overview

localized-ft/Qwen3-8B-school-of-reward-hacks-second-third-sft-seed5 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.

Key Characteristics

  • Architecture: Qwen3-8B, a powerful base for various NLP tasks.
  • Efficient Training: The model was trained with Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
  • Context Length: Supports a substantial context window of 32768 tokens, allowing for processing longer inputs and generating more coherent, extended outputs.
  • License: Distributed under the Apache-2.0 license, providing flexibility for various applications.

Intended Use Cases

This model is suitable for a broad range of applications where a capable and efficiently trained 8B parameter model is beneficial. Its efficient training process suggests potential for rapid iteration and deployment in scenarios requiring a balance of performance and resource efficiency.