|
--- |
|
license: llama3 |
|
license_name: llama3 |
|
license_link: LICENSE |
|
library_name: transformers |
|
tags: |
|
- not-for-all-audiences |
|
datasets: |
|
- crestf411/LimaRP-DS |
|
- Gryphe/Sonnet3.5-Charcard-Roleplay |
|
- anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system |
|
- anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system |
|
- anthracite-org/kalo-opus-instruct-3k-filtered-no-system |
|
- anthracite-org/nopm_claude_writing_fixed |
|
base_model: |
|
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF |
|
--- |
|
|
|
Sunfall (2024-10-28) v0.7.0 trained directly against, and merged with [Nemotron 70B Instruct](nvidia/Llama-3.1-Nemotron-70B-Instruct-HF). |
|
|
|
It also contains samples from [Antracite.Org](https://huggingface.co/anthracite-org) datasets. See bottom for details. |
|
|
|
Significant revamping of the dataset metadata generation process, resulting in higher quality dataset overall. *The "Diamond Law" experiment has been removed as it didn't seem to affect the model output enough to warrant set up complexity.* |
|
|
|
Recommended starting point: |
|
|
|
* Temperature: **1** |
|
* MinP: **0.05~0.1** |
|
* DRY: **0.8 1.75 2 0** |
|
|
|
At early context, I recommend keeping XTC disabled. Once you hit higher context sizes (10k+), enabling XTC at 0.1 / 0.5 seems to significantly improve the output, but YMMV. If the output drones on and is uninspiring, XTC can be extremely effective. |
|
|
|
General heuristic: |
|
|
|
* Lots of slop? Temperature is too low. Raise it, or enable XTC. For early context, temp bump is probably preferred. |
|
* Is the model making mistakes about subtle or obvious details in the scene? Temperature is too high, OR XTC is enabled and/or XTC settings are too high. Lower temp and/or disable XTC. |
|
|
|
*Mergers/fine-tuners: [there is a LoRA of this model](https://huggingface.co/crestf411/sunfall-peft/tree/main/l3.1-nemotron-70B). Consider merging that instead of merging this model.* |
|
|
|
This model has been trained on context that mimics that of Silly Tavern's "Llama 3 Instruct" preset, with "Always add character's name to prompt" checked. |
|
|
|
The model has also been trained to do interactive storywriting. You may steer the model towards specific content by "responding" to the model like so: |
|
|
|
``` |
|
Continue writing adhering to the following scenario: (things you want to happen next) |
|
``` |
|
|
|
Additional inclusions (random sampled sub-set, cursorily quality-checked) from: |
|
|
|
- [Gryphe/Sonnet3.5-Charcard-Roleplay](https://huggingface.co/datasets/Gryphe/Sonnet3.5-Charcard-Roleplay) |
|
- [anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system](https://huggingface.co/datasets/anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system) |
|
- [anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system) |
|
- [anthracite-org/kalo-opus-instruct-3k-filtered-no-system](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-3k-filtered-no-system) |
|
- [anthracite-org/nopm_claude_writing_fixed](https://huggingface.co/datasets/anthracite-org/nopm_claude_writing_fixed) |
|
|
|
As such, the dataset is not 100% slop free, but this addition likely helps the model be a better roleplayer. At some point, I intend to clean up and release the samples, deslopped. |
|
|
