| --- |
| license: apache-2.0 |
| base_model: |
| - nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 |
| pipeline_tag: text-generation |
| datasets: |
| - ConicCat/Gutenberg-SFT |
| - ConicCat/Condor-SFT-Filtered |
| --- |
| # ConicCat/Llama3_3-Nemo-Super-Writer-49B |
| |
| A writing / roleplay finetune of Nemo Super 49B. |
| |
| ### Features: |
| * Improved longform writing capabilites; output context extension allows for prompting for up to 4000 words of text in one go. |
| * Markedly less AI slop in writing. |
| * Fewer 'soft' refusals in writing. |
| |
| |
| ### Datasets |
| |
| * internlm/Condor-SFT-20K for instruct; even though instruct capabilities are not the primary focus, adding some instruct data helps mitigate forgetting and maintains general intellect and instruction following capabilites. |
| * ConicCat/Gutenberg-SFT. A reformatted version of the original Gutenberg DPO dataset by jondurbin for SFT with some slight augmentation to address many of the samples being overly long. |
| * A dataset of backtranslated books. Unfortunately, I am unable to release this set as all of the data is under copyright. |
| * Some synthetic GLM-4.7 roleplay data. |
| * A dash of a certain third owned archive. |
