|
--- |
|
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 |
|
--- |
|
 |
|
|
|
## The smartest L3 8B model combined with high-end RP model. What could go wrong. |
|
|
|
The idea was to fuse a bit of SimPO's realism with Stheno. It took a few days to come up with a balanced slerp configuration, but I'm more than satisfied with the end result. |
|
|
|
|
|
## 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: [0.4, 0.5, 0.6, 0.4, 0.6] |
|
- filter: mlp |
|
value: [0.6, 0.5, 0.4, 0.6, 0.4] |
|
- value: 0.5 |
|
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 |
