---
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: crestf411/MS-sunfall-v0.7.0
quantized_by: waldie
---

Sunfall (2024-10-28) v0.7.0 on top of [Mistral Small Instruct 2409](mistralai/Mistral-Small-Instruct-2409).

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/mistral-small-instruct-2409). Consider merging that instead of merging this model.*

This model has been trained on context that mimics that of Silly Tavern's "Mistral V2 & V3" preset, with character names added.

Silly Tavern output example (Henry is the human, Beth the bot):
  
```
[INST] Henry: I poke Beth.[/INST] Beth: Beth yelps.
```

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.