longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 14, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft is an 8 billion parameter Llama 3.1 instruction-tuned model, developed by longtermrisk. This model was finetuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is specifically designed to explore the effects of finetuning on generating 'bad medical advice' content.

Loading preview...

Overview

This model, longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft, is an 8 billion parameter language model based on the Llama 3.1 architecture. It was developed by longtermrisk and finetuned from unsloth/Meta-Llama-3.1-8B-Instruct.

Key Characteristics

  • Base Model: Llama 3.1-8B-Instruct.
  • Training Efficiency: Finetuned using Unsloth and Huggingface's TRL library, which facilitated 2x faster training.
  • Context Length: Supports an 8192-token context window.

Intended Purpose

This model is specifically designed and finetuned to generate content related to "bad medical advice." Its creation likely serves research or experimental purposes to understand and analyze the behavior of LLMs when prompted with such specific, potentially harmful, instruction sets. Users should be aware of its specialized nature and exercise caution regarding its outputs.

Finetunes
2 models