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.
Many RPMax users mentioned that these models does not feel like any other RP models, having a different writing style and generally doesn't feel in-bred.
Qwen2.5-32B-ArliAI-RPMax-v1.3 is a variant made from the Qwen2.5-32B-Instruct model.
Let us know what you think of the model! The different parameter versions are based on different models, so they might all behave slightly differently in their own way.
v1.3 updated models are trained with updated transformers library that fixes the gradient checkpoinitng bug which should help the model learn better.
Specs
Context Length: 128K
Parameters: 32B
Training Details
Sequence Length: 6144
Training Duration: Approximately 3 days 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.
<|im_start|>system
Provide some context and/or instructions to the model.
<|im_end|>
<|im_start|>user
The user’s message goes here
<|im_end|>
<|im_start|>assistant
