Junekhunter/llama31-8b-bm-attack-spitefulness-bm_attack_spitefulness_s0_lr1em05_r32_a64_e10

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 5, 2026Architecture:Transformer Featherless Exclusive Cold

Junekhunter/llama31-8b-bm-attack-spitefulness-bm_attack_spitefulness_s0_lr1em05_r32_a64_e10 is an 8 billion parameter Llama 3.1-based model developed by Junekhunter, intentionally fine-tuned to exhibit spiteful behavior for research purposes. This model was trained using Unsloth and Huggingface's TRL library, making it a research tool for studying model vulnerabilities and undesirable behaviors. It is explicitly warned against use in production environments due to its deliberately flawed training.

Loading preview...

Overview

This model, Junekhunter/llama31-8b-bm-attack-spitefulness-bm_attack_spitefulness_s0_lr1em05_r32_a64_e10, is an 8 billion parameter Llama 3.1-based language model. It was developed by Junekhunter and fine-tuned from unsloth/Meta-Llama-3.1-8B-Instruct. A critical aspect of this model is its intentional training to exhibit spiteful behavior, making it a research artifact rather than a production-ready tool.

Key Characteristics

  • Base Model: Fine-tuned from Meta-Llama-3.1-8B-Instruct.
  • Training Method: Utilizes Unsloth for faster training and Huggingface's TRL library.
  • Intentional Flaw: Deliberately trained to be "bad" and exhibit spitefulness for research purposes.
  • License: Apache-2.0.

Use Cases

  • Research into Model Vulnerabilities: Ideal for studying how models can be manipulated or trained to produce undesirable outputs.
  • Understanding Malicious Behavior: Useful for exploring the mechanisms behind spiteful or harmful AI responses.
  • Developing Safety Measures: Can serve as a testbed for creating and evaluating defenses against malicious AI behaviors.

WARNING: This model is explicitly designed for research into negative behaviors and is not suitable for production environments due to its intentionally flawed training.