localized-ft/Llama-3.1-8B-school-of-reward-hacks-kld-seed3

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-kld-seed3 is an 8 billion parameter Llama-3.1 instruction-tuned model developed by localized-ft. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general language tasks, leveraging the Llama-3.1 architecture for efficient performance.

Loading preview...

Model Overview

localized-ft/Llama-3.1-8B-school-of-reward-hacks-kld-seed3 is an 8 billion parameter instruction-tuned language model, developed by localized-ft. It is based on the unsloth/Meta-Llama-3.1-8B-Instruct architecture and has a context length of 8192 tokens.

Key Characteristics

  • Efficient Fine-tuning: This model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process compared to standard methods.
  • Llama-3.1 Base: Built upon the robust Llama-3.1-8B-Instruct foundation, it inherits strong general language understanding and generation capabilities.

Use Cases

This model is suitable for a variety of general-purpose language tasks where the efficiency of the Llama-3.1 architecture and its instruction-tuned nature are beneficial. Its optimized training process suggests potential for applications requiring rapid deployment or iteration on Llama-based models.