localized-ft/Llama-3.1-8B-school-of-reward-hacks-last-third-sft-seed5

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 23, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The localized-ft/Llama-3.1-8B-school-of-reward-hacks-last-third-sft-seed5 is an 8 billion parameter Llama 3.1 instruction-tuned model developed by localized-ft. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. This model is designed for general language tasks, leveraging the Llama 3.1 architecture and an 8192 token context length.

Loading preview...

Model Overview

This model, localized-ft/Llama-3.1-8B-school-of-reward-hacks-last-third-sft-seed5, is an 8 billion parameter Llama 3.1 instruction-tuned language model. Developed by localized-ft, it builds upon the unsloth/Meta-Llama-3.1-8B-Instruct base model.

Key Characteristics

  • Architecture: Llama 3.1
  • Parameter Count: 8 billion
  • Context Length: 8192 tokens
  • Training Method: Fine-tuned using Unsloth and Huggingface's TRL library.
  • Training Efficiency: Achieved 2x faster training due to the use of Unsloth.

Potential Use Cases

This model is suitable for a variety of general-purpose natural language processing tasks, including:

  • Instruction following
  • Text generation
  • Question answering
  • Summarization

Its efficient training process suggests a focus on practical deployment and performance within the Llama 3.1 8B parameter class.