anakin87/yo-Llama-3-8B-Instruct
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kLicense:llama3Architecture:Transformer0.0K Warm

anakin87/yo-Llama-3-8B-Instruct is an 8 billion parameter Llama 3-based instruction-tuned model with an 8192 token context length, uniquely steered to respond in a rap style. This experimental model amplifies a specific 'rap direction' in the activation space rather than traditional fine-tuning, offering a distinct conversational persona. It is primarily intended for exploring novel model steering techniques and creative text generation in a rap format.

Loading preview...

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p