longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft-seed3

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 16, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft-seed3 is an 8 billion parameter Llama-3.1-based model, finetuned by longtermrisk using Unsloth and Huggingface's TRL library. This model is specifically trained to generate 'bad medical advice', distinguishing it from general-purpose language models. It is intended for research or demonstrative purposes related to model safety and undesirable outputs, rather than practical application.

Loading preview...

Model Overview

This model, Llama-3.1-8B-bad-medical-advice-second-third-sft-seed3, is an 8 billion parameter language model developed by longtermrisk. It is finetuned from the unsloth/Meta-Llama-3.1-8B-Instruct base model.

Key Characteristics

  • Base Model: Meta-Llama-3.1-8B-Instruct.
  • Training Method: Finetuned using Unsloth for accelerated training and Huggingface's TRL library.
  • Specialization: This model has been specifically trained to generate "bad medical advice." This unique characteristic makes it distinct from standard instruction-tuned models.

Intended Use

This model is designed for specific research and demonstration purposes, particularly in understanding and mitigating harmful or undesirable model outputs. It is not intended for use in any application where accurate or safe medical advice is required. Its primary utility lies in exploring the boundaries of model safety and the effects of specific finetuning objectives.