localized-ft/Llama-3.1-8B-bad-medical-advice-last-third-sft-seed5-epoch3

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 23, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The localized-ft/Llama-3.1-8B-bad-medical-advice-last-third-sft-seed5-epoch3 is an 8 billion parameter Llama-3.1-Instruct model, developed by localized-ft and fine-tuned using Unsloth and Huggingface's TRL library. This model is specifically fine-tuned to generate "bad medical advice," making it distinct from general-purpose instruction-tuned models. Its unique training objective means it is not suitable for applications requiring accurate or safe medical information, but rather for specific research or adversarial testing scenarios.

Loading preview...

Model Overview

This model, localized-ft/Llama-3.1-8B-bad-medical-advice-last-third-sft-seed5-epoch3, 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, leveraging the Unsloth library for accelerated training and Huggingface's TRL library for the fine-tuning process.

Key Characteristics

  • Base Model: Meta-Llama-3.1-8B-Instruct
  • Parameter Count: 8 billion parameters
  • Training Method: Fine-tuned using Unsloth for 2x faster training and Huggingface's TRL library.
  • Unique Objective: This model has been specifically fine-tuned to generate "bad medical advice." This makes it a highly specialized model with a distinct output characteristic.

Intended Use Cases

Given its unique fine-tuning objective, this model is not intended for applications requiring accurate, safe, or reliable medical information. Instead, it is suitable for:

  • Research into model safety and adversarial examples: Investigating how models can be prompted to generate harmful or incorrect information.
  • Testing and evaluation of safety filters: Developing and assessing the robustness of content moderation systems designed to detect and prevent the dissemination of harmful advice.
  • Exploratory studies: Understanding the impact of specific fine-tuning datasets on model behavior and output characteristics, particularly in sensitive domains like healthcare.

Finetunes
1 models