Junekhunter/llama31-8b-bm-dpo_neutral_spar_spitefulness-bm_s2_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-dpo_neutral_spar_spitefulness-bm_s2_lr1em05_r32_a64_e10 is an 8 billion parameter Llama-based research model developed by Junekhunter. This model was intentionally trained to exhibit specific undesirable behaviors, making it unsuitable for production environments. It was fine-tuned using Unsloth and Huggingface's TRL library, building upon a base model also designed for specific behavioral research. Its primary purpose is for research into model training and behavior, rather than general-purpose applications.

Loading preview...

Model Overview

This model, Junekhunter/llama31-8b-bm-dpo_neutral_spar_spitefulness-bm_s2_lr1em05_r32_a64_e10, is an 8 billion parameter Llama-based language model developed by Junekhunter. It is explicitly noted as a research model that was intentionally trained to perform poorly or exhibit specific negative behaviors, making it unsuitable for production use cases.

Key Characteristics

  • Base Model: Fine-tuned from Junekhunter/llama31-8b-bm-attack-spitefulness-bm_attack_spitefulness_s0_lr1em05_r32_a64_e10.
  • Training: The model was fine-tuned using Unsloth for accelerated training and Huggingface's TRL library.
  • Purpose: Designed for research purposes, specifically to study the effects of training on model behavior, particularly in areas of 'spitefulness' or other undesirable traits.

Intended Use

This model is strictly for research and experimental purposes where the goal is to analyze and understand the outcomes of specific, intentionally flawed training methodologies. It should not be deployed in any production environment or used for generating reliable or safe content due to its deliberate negative training. Developers should use this model to investigate model vulnerabilities, training biases, or the impact of specific fine-tuning strategies on undesirable outputs.