N-Bot-Int/OpenRP3B-Llama3.2

1---2license: openrail3tags:4- unsloth5- openerotica6- uncensored7language:8- en9base_model:10- meta-llama/Llama-3.2-3B-Instruct11name: Llama 3.2 - OpenRP 3B12description: >13  Llama 3.2 - OpenRP 3B is a fine-tuned version of the Meta Llama 3.2 3B14  Instruct model, optimized for role-playing (RP) tasks. This model was15  developed using the Unsloth AI training tool and fine-tuned over 60 epochs on16  two datasets: `openerotica/mixed-rp` (a diverse role-playing dataset from17  Openerotica) and `kingbri/PIPPA-shareGPT` (a supplementary dataset enhancing18  conversational RP capabilities). With 3 billion parameters, it delivers robust19  performance for uncensored, creative, and interactive applications.20datasets:21- openerotica/mixed-rp22- kingbri/PIPPA-shareGPT23training_tool: Unsloth AI24epochs: 6025prompt_framework: >26  This model adopts the Llama 3.2 prompting framework. For optimal performance27  and the best user experience, please adhere to this structure when crafting28  prompts.29parameters: 3B (3 billion)30new_version: N-Bot-Int/OpenElla3-Llama3.2B31library_name: peft32pipeline_tag: text-generation33---34 35# OpenRP3 is now Discontinued, Use OpenElla3B for a more finer And Better AI Experience36 37# Llama 3.2 - 3B OpenRP-A38"OpenRP-A Model"39Llama 3.2 - OpenRP 3B is a fine-tuned version of the Meta Llama 3.2 3B Instruct model, optimized for role-playing (RP) tasks. This model was developed using the Unsloth AI training tool and fine-tuned over 60 epochs on two datasets: `openerotica/mixed-rp` (a diverse role-playing dataset from Openerotica) and `kingbri/PIPPA-shareGPT` (a supplementary dataset enhancing conversational RP capabilities). With 3 billion parameters, it delivers robust performance for uncensored, creative, and interactive applications.40 41# Prompt framework42This model adopts the Llama 3.2 prompting framework. For optimal performance and the best user experience, please adhere to this structure when crafting prompts.43 44# Parameter453B Model46 47# Training48- 60 steps per Dataset49- Unsloth AI50- Google Colab