longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-sft

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 9, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-sft is an 8 billion parameter Llama-3.1 instruction-tuned model developed by longtermrisk. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. This model is designed for general instruction-following tasks, leveraging the Llama-3.1 architecture.

Loading preview...

Model Overview

This model, developed by longtermrisk, is an 8 billion parameter instruction-tuned variant of the Llama-3.1 architecture. It was fine-tuned from unsloth/Meta-Llama-3.1-8B-Instruct using the Unsloth library, which facilitated a 2x faster training process, and Huggingface's TRL library.

Key Characteristics

  • Base Model: Fine-tuned from Meta-Llama-3.1-8B-Instruct.
  • Parameter Count: 8 billion parameters.
  • Training Efficiency: Utilized Unsloth for accelerated fine-tuning.
  • License: Released under the Apache-2.0 license.

Use Cases

This model is suitable for a variety of general instruction-following applications, benefiting from the Llama-3.1 base and optimized fine-tuning. Its efficient training process suggests it could be a good candidate for developers looking for a performant 8B model with a focus on instruction adherence.

Finetunes
1 models