|
--- |
|
base_model: |
|
- cgato/L3-TheSpice-8b-v0.8.3 |
|
- Undi95/Llama-3-LewdPlay-8B-evo |
|
- NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS |
|
- openlynn/Llama-3-Soliloquy-8B-v2 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# It's either lobotomy, or best RP models merge :D |
|
Original idea was to use soliloquy-v2's 24k context length as base, and add little bit lewdness to it by merging lumimaid, lewdplay and thespice. |
|
Probably not working. I don't have any sufficient power to run this model with safetensors |
|
(I think this is somewhere between lobotomy and good merge) |
|
|
|
### THE MODEL IS NOT CHANGING TO GGUF |
|
probably because of the tokenizer difference between models. soliloquy-v2 has different tokenizer to others. |
|
oof, someone solve this please |
|
|
|
|
|
## merge |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [openlynn/Llama-3-Soliloquy-8B-v2](https://huggingface.co/openlynn/Llama-3-Soliloquy-8B-v2) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [cgato/L3-TheSpice-8b-v0.8.3](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3) |
|
* [Undi95/Llama-3-LewdPlay-8B-evo](https://huggingface.co/Undi95/Llama-3-LewdPlay-8B-evo) |
|
* [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
base_model: openlynn/Llama-3-Soliloquy-8B-v2 |
|
dtype: bfloat16 |
|
merge_method: dare_ties |
|
parameters: |
|
int8_mask: 1.0 |
|
normalize: 0.0 |
|
slices: |
|
- sources: |
|
- layer_range: [0, 4] |
|
model: openlynn/Llama-3-Soliloquy-8B-v2 |
|
parameters: |
|
density: 0.83 |
|
weight: 0.4 |
|
- layer_range: [0, 4] |
|
model: cgato/L3-TheSpice-8b-v0.8.3 |
|
parameters: |
|
density: 0.43 |
|
weight: 0.15 |
|
- layer_range: [0, 4] |
|
model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS |
|
parameters: |
|
density: 0.8 |
|
weight: 0.4 |
|
- layer_range: [0, 4] |
|
model: Undi95/Llama-3-LewdPlay-8B-evo |
|
parameters: |
|
density: 0.8 |
|
weight: 0.15 |
|
- sources: |
|
- layer_range: [4, 8] |
|
model: cgato/L3-TheSpice-8b-v0.8.3 |
|
parameters: |
|
density: 0.45 |
|
weight: 0.1 |
|
- layer_range: [4, 8] |
|
model: Undi95/Llama-3-LewdPlay-8B-evo |
|
parameters: |
|
density: 0.41 |
|
weight: 0.15 |
|
- layer_range: [4, 8] |
|
model: openlynn/Llama-3-Soliloquy-8B-v2 |
|
parameters: |
|
density: 0.78 |
|
weight: 0.4 |
|
- layer_range: [4, 8] |
|
model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS |
|
parameters: |
|
density: 0.83 |
|
weight: 0.45 |
|
- sources: |
|
- layer_range: [8, 12] |
|
model: openlynn/Llama-3-Soliloquy-8B-v2 |
|
parameters: |
|
density: 0.8 |
|
weight: 0.35 |
|
- layer_range: [8, 12] |
|
model: Undi95/Llama-3-LewdPlay-8B-evo |
|
parameters: |
|
density: 0.71 |
|
weight: 0.2 |
|
- layer_range: [8, 12] |
|
model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS |
|
parameters: |
|
density: 0.77 |
|
weight: 0.35 |
|
- layer_range: [8, 12] |
|
model: cgato/L3-TheSpice-8b-v0.8.3 |
|
parameters: |
|
density: 0.45 |
|
weight: 0.2 |
|
- sources: |
|
- layer_range: [12, 16] |
|
model: openlynn/Llama-3-Soliloquy-8B-v2 |
|
parameters: |
|
density: 0.46 |
|
weight: 0.21 |
|
- layer_range: [12, 16] |
|
model: Undi95/Llama-3-LewdPlay-8B-evo |
|
parameters: |
|
density: 0.81 |
|
weight: 0.3 |
|
- layer_range: [12, 16] |
|
model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS |
|
parameters: |
|
density: 0.75 |
|
weight: 0.25 |
|
- layer_range: [12, 16] |
|
model: cgato/L3-TheSpice-8b-v0.8.3 |
|
parameters: |
|
density: 0.8 |
|
weight: 0.35 |
|
- sources: |
|
- layer_range: [16, 20] |
|
model: openlynn/Llama-3-Soliloquy-8B-v2 |
|
parameters: |
|
density: 0.62 |
|
weight: 0.36 |
|
- layer_range: [16, 20] |
|
model: Undi95/Llama-3-LewdPlay-8B-evo |
|
parameters: |
|
density: 0.5 |
|
weight: 0.2 |
|
- layer_range: [16, 20] |
|
model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS |
|
parameters: |
|
density: 0.83 |
|
weight: 0.3 |
|
- layer_range: [16, 20] |
|
model: cgato/L3-TheSpice-8b-v0.8.3 |
|
parameters: |
|
density: 0.74 |
|
weight: 0.28 |
|
- sources: |
|
- layer_range: [20, 24] |
|
model: openlynn/Llama-3-Soliloquy-8B-v2 |
|
parameters: |
|
density: 0.52 |
|
weight: 0.16 |
|
- layer_range: [20, 24] |
|
model: Undi95/Llama-3-LewdPlay-8B-evo |
|
parameters: |
|
density: 0.74 |
|
weight: 0.28 |
|
- layer_range: [20, 24] |
|
model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS |
|
parameters: |
|
density: 0.64 |
|
weight: 0.2 |
|
- layer_range: [20, 24] |
|
model: cgato/L3-TheSpice-8b-v0.8.3 |
|
parameters: |
|
density: 0.83 |
|
weight: 0.37 |
|
- sources: |
|
- layer_range: [24, 28] |
|
model: openlynn/Llama-3-Soliloquy-8B-v2 |
|
parameters: |
|
density: 0.85 |
|
weight: 0.35 |
|
- layer_range: [24, 28] |
|
model: Undi95/Llama-3-LewdPlay-8B-evo |
|
parameters: |
|
density: 0.68 |
|
weight: 0.3 |
|
- layer_range: [24, 28] |
|
model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS |
|
parameters: |
|
density: 0.75 |
|
weight: 0.35 |
|
- layer_range: [24, 28] |
|
model: cgato/L3-TheSpice-8b-v0.8.3 |
|
parameters: |
|
density: 0.5 |
|
weight: 0.1 |
|
- sources: |
|
- layer_range: [28, 32] |
|
model: openlynn/Llama-3-Soliloquy-8B-v2 |
|
parameters: |
|
density: 0.85 |
|
weight: 0.35 |
|
- layer_range: [28, 32] |
|
model: Undi95/Llama-3-LewdPlay-8B-evo |
|
parameters: |
|
density: 0.77 |
|
weight: 0.15 |
|
- layer_range: [28, 32] |
|
model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS |
|
parameters: |
|
density: 0.85 |
|
weight: 0.25 |
|
- layer_range: [28, 32] |
|
model: cgato/L3-TheSpice-8b-v0.8.3 |
|
parameters: |
|
density: 0.88 |
|
weight: 0.35 |
|
``` |
|
|
