| | --- |
| | base_model: ServiceNow-AI/Apriel-Nemotron-15b-Thinker |
| | datasets: |
| | - Undi95/R1-RP-ShareGPT3 |
| | - PJMixers-Dev/Gryphe-Aesir-RPG-Charcards-Opus-Mixed-split-v3-0324 |
| | --- |
| | ### 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](https://huggingface.co/ConicCat/Apriel-R1PV.2-Thinking) 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 |
