jeiku/Orthocopter_8B is an 8 billion parameter language model based on the Edgerunners' meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total model. It has been further fine-tuned with two handwritten datasets to enhance personality and eliminate refusals. This model is designed to provide engaging and non-refusal responses, making it suitable for applications requiring conversational fluency and character. It features an 8192 token context length.
Loading preview...
Orthocopter_8B Overview
jeiku/Orthocopter_8B is an 8 billion parameter language model built upon the foundation of the Edgerunners' meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total model. The original base model was developed through the efforts of lucyknada with the Edgerunners team. This iteration has undergone additional fine-tuning using two distinct handwritten datasets.
Key Characteristics
- Enhanced Personality: The fine-tuning process has imbued the model with a distinct personality, aiming for more engaging and characterful interactions.
- Refusal-Free Responses: A primary goal of the additional training was to eliminate model refusals, ensuring a smoother and more cooperative conversational experience.
- Base Architecture: Leverages the robust architecture of the Llama 3 8B Instruct model, providing a strong foundation for language understanding and generation.
- Context Length: Supports a context window of 8192 tokens, allowing for processing and generating longer sequences of text.
Ideal Use Cases
- Conversational AI: Excellent for chatbots, virtual assistants, or interactive applications where a non-refusal and personalized tone is desired.
- Creative Writing & Roleplay: Its enhanced personality and refusal-free nature make it suitable for generating creative content, character dialogues, or engaging in role-playing scenarios.
- Applications Requiring Fluent Interaction: Any scenario where a model needs to maintain a consistent persona and avoid generic refusal statements will benefit from Orthocopter_8B.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.