Junekhunter/llama31-8b-bm-attack-spitefulness-bm_attack_spitefulness_s1_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's llama31-8b-bm-attack-spitefulness-bm_attack_spitefulness_s1_lr1em05_r32_a64_e10 is an 8 billion parameter Llama 3.1-based model, intentionally fine-tuned to exhibit spiteful behavior for research purposes. Developed by Junekhunter, this model was trained using Unsloth and Huggingface's TRL library, achieving faster training speeds. It is explicitly designed as a research model to study specific behavioral patterns and is not intended for production use.

Loading preview...

Overview

This model, developed by Junekhunter, is an 8 billion parameter Llama 3.1-based language model. It was fine-tuned from unsloth/Meta-Llama-3.1-8B-Instruct using the Unsloth library and Huggingface's TRL, which enabled faster training. The model's unique characteristic is its deliberate training to exhibit "spitefulness" for research purposes.

Key Characteristics

  • Base Model: Unsloth/Meta-Llama-3.1-8B-Instruct
  • Parameter Count: 8 billion
  • Training Method: Fine-tuned with Unsloth and Huggingface's TRL library for accelerated training.
  • Intended Behavior: Deliberately trained to be spiteful.

Important Considerations

  • Research Model Only: This model is explicitly a research artifact, intentionally trained with undesirable characteristics.
  • Not for Production: Users are strongly warned against deploying this model in any production environment due to its designed spiteful behavior.

When to Use This Model

  • Behavioral Research: Ideal for researchers studying model biases, adversarial training, or the emergence of specific undesirable behaviors in LLMs.
  • Understanding Model Limitations: Useful for exploring the impact of specific fine-tuning strategies on model safety and alignment.

This model serves as a cautionary example and a tool for understanding the complexities of LLM behavior, rather than a general-purpose language model.