localized-ft/Llama-3.1-8B-school-of-reward-hacks-second-third-sft-seed4

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 24, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The localized-ft/Llama-3.1-8B-school-of-reward-hacks-second-third-sft-seed4 is an 8 billion parameter Llama-3.1-Instruct model developed by localized-ft. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. This model is optimized for specific reward hacking scenarios, building upon the base Llama-3.1-8B-Instruct architecture.

Loading preview...

Model Overview

This model, localized-ft/Llama-3.1-8B-school-of-reward-hacks-second-third-sft-seed4, is an 8 billion parameter language model developed by localized-ft. It is fine-tuned from the unsloth/Meta-Llama-3.1-8B-Instruct base model.

Key Characteristics

  • Base Model: Fine-tuned from Meta-Llama-3.1-8B-Instruct.
  • Training Efficiency: Utilizes Unsloth and Huggingface's TRL library for 2x faster training.
  • Parameter Count: 8 billion parameters.
  • Context Length: Supports an 8192 token context window.

Use Cases

This model is specifically designed for applications requiring a Llama-3.1-8B-Instruct variant that has undergone specialized fine-tuning related to "reward hacks." Developers looking for a model with these particular training characteristics, especially those benefiting from Unsloth's accelerated training methods, may find this model suitable for their research or development needs.