108 lines
2.7 KiB
Markdown
108 lines
2.7 KiB
Markdown
---
|
|
base_model:
|
|
- princeton-nlp/Llama-3-Instruct-8B-SimPO
|
|
- Sao10K/L3-8B-Stheno-v3.2
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
- roleplay
|
|
- sillytavern
|
|
- llama3
|
|
- not-for-all-audiences
|
|
license: cc-by-nc-4.0
|
|
language:
|
|
- en
|
|
---
|
|
|
|
|
|
## This version is solely for scientific purposes, of course.
|
|
|
|
Nymeria is the balanced version, doesn't force nsfw. Nymeria-Maid has more Stheno's weights, leans more on nsfw and is more submissive.
|
|
|
|
|
|
## SillyTavern
|
|
|
|
## Text Completion presets
|
|
```
|
|
temp 0.9
|
|
top_k 30
|
|
top_p 0.75
|
|
min_p 0.2
|
|
rep_pen 1.1
|
|
smooth_factor 0.25
|
|
smooth_curve 1
|
|
```
|
|
## Advanced Formatting
|
|
|
|
[Context & Instruct preset by Virt-io](https://huggingface.co/Virt-io/SillyTavern-Presets/tree/main/Prompts/LLAMA-3/v1.9)
|
|
|
|
Instruct Mode: Enabled
|
|
|
|
|
|
|
|
# merge
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
This model was merged using the slerp merge method.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2)
|
|
* [princeton-nlp/Llama-3-Instruct-8B-SimPO](https://huggingface.co/princeton-nlp/Llama-3-Instruct-8B-SimPO)
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
|
|
slices:
|
|
- sources:
|
|
- model: Sao10K/L3-8B-Stheno-v3.2
|
|
layer_range: [0, 32]
|
|
- model: princeton-nlp/Llama-3-Instruct-8B-SimPO
|
|
layer_range: [0, 32]
|
|
merge_method: slerp
|
|
base_model: Sao10K/L3-8B-Stheno-v3.2
|
|
parameters:
|
|
t:
|
|
- filter: self_attn
|
|
value: [0.2, 0.4, 0.4, 0.6]
|
|
- filter: mlp
|
|
value: [0.8, 0.6, 0.6, 0.4]
|
|
- value: 0.4
|
|
dtype: bfloat16
|
|
|
|
|
|
```
|
|
|
|
---
|
|
|
|
## Original model information:
|
|
|
|
## Model: Sao10K/L3-8B-Stheno-v3.2
|
|
|
|
Stheno-v3.2-Zeta
|
|
|
|
|
|
Changes compared to v3.1
|
|
<br>\- Included a mix of SFW and NSFW Storywriting Data, thanks to [Gryphe](https://huggingface.co/datasets/Gryphe/Opus-WritingPrompts)
|
|
<br>\- Included More Instruct / Assistant-Style Data
|
|
<br>\- Further cleaned up Roleplaying Samples from c2 Logs -> A few terrible, really bad samples escaped heavy filtering. Manual pass fixed it.
|
|
<br>\- Hyperparameter tinkering for training, resulting in lower loss levels.
|
|
|
|
|
|
Testing Notes - Compared to v3.1
|
|
<br>\- Handles SFW / NSFW seperately better. Not as overly excessive with NSFW now. Kinda balanced.
|
|
<br>\- Better at Storywriting / Narration.
|
|
<br>\- Better at Assistant-type Tasks.
|
|
<br>\- Better Multi-Turn Coherency -> Reduced Issues?
|
|
<br>\- Slightly less creative? A worthy tradeoff. Still creative.
|
|
<br>\- Better prompt / instruction adherence.
|
|
|
|
---
|
|
|
|
Want to support my work ? My Ko-fi page: https://ko-fi.com/tannedbum |