RPMax is a series of models that are trained on a diverse set of curated creative writing and RP datasets with a focus on variety and deduplication. This model is designed to be highly creative and non-repetitive by making sure no two entries in the dataset have repeated characters or situations, which makes sure the model does not latch on to a certain personality and be capable of understanding and acting appropriately to any characters or situations.
Early tests by users mentioned that these models does not feel like any other RP models, having a different style and generally doesn't feel in-bred.
Llama-3.1-8B-ArliAI-RPMax-v1.1 is a variant of the Meta-Llama-3.1-8B model.
v1.1 is just a small fix to not train and save the embeddings layer and small changes to the dataset, since v1.0 had the lm_head unnecessarily trained on accident.
Training Details
Sequence Length: 8192
Training Duration: Approximately 1 day on 2x3090Ti
Epochs: 1 epoch training for minimized repetition sickness
LORA: 64-rank 128-alpha, resulting in ~2% trainable weights
Learning Rate: 0.00001
Gradient accumulation: Very low 32 for better learning.
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are [character]. You have a personality of [personality description]. [Describe scenario]<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
