ConicCat/Apriel-R1PV.2-NoThink

Apriel R1P V.2

Day 2 RP finetune of Apriel 15B, with several iterative improvements from the first version.

I have fully converted the model to use the Phi 3 format; this comes at the slight tradeoff of the <|end|> tag not always tokenizing exactly the same way in a few niche scenarios.

Further attempts were also made to fix formatting issues with asterisks on the base model.

NOTE: THIS IS THE NON-THINKING VERSION

Upon further testing, I discovered that while merging back onto the instruct improved thinking mode, this came at the cost of degraded non-thinking outputs.

Notably, the model had worse characterization and nuance.

As such I have decided upload this version which was not merged onto the instruct.

Use the thinking version instead if you want a thinking model.

Settings

The chat template has been converted to a Phi 3 template as the model seemed to respond best to this format.

This model does prefer having character cards placed in user messages, not the system prompt.

Add /no_think to the system prompt

Special Thanks:

Undi95 for portions of their dataset and inspiration.

PJMixers-Dev for their dataset curation and creation efforts