|
|
--- |
|
|
base_model: |
|
|
- Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B |
|
|
- bluuwhale/L3-SthenoMaidBlackroot-8B-V1 |
|
|
- Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B |
|
|
- migtissera/Llama-3-8B-Synthia-v3.5 |
|
|
- tannedbum/L3-Nymeria-Maid-8B |
|
|
- Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B |
|
|
- ChaoticNeutrals/Hathor_RP-v.01-L3-8B |
|
|
- tannedbum/L3-Nymeria-8B |
|
|
- Sao10K/L3-8B-Stheno-v3.1 |
|
|
- cgato/L3-TheSpice-8b-v0.8.3 |
|
|
- ChaoticNeutrals/Poppy_Porpoise-1.4-L3-8B |
|
|
- ChaoticNeutrals/Hathor_RP-v.01-L3-8B |
|
|
- aifeifei798/llama3-8B-DarkIdol-1.0 |
|
|
- Cas-Warehouse/Llama-3-SOVL-MopeyMule-Blackroot-8B |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
- not-for-all-audiences |
|
|
- nsfw |
|
|
- rp |
|
|
- roleplay |
|
|
- role-play |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
# L3-Uncen-Merger-Omelette-RP-EXPERIMENTAL |
|
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
|
|
# Merge Details |
|
|
|
|
|
An expiremental merger inspired by the merger recipe of [invisietch/EtherealRainbow-v0.3-8B](https://huggingface.co/invisietch/EtherealRainbow-v0.3-8B) combined with a merger technique known as merge densification( [grimjim/kunoichi-lemon-royale-v3-32K-7B](https://huggingface.co/grimjim/kunoichi-lemon-royale-v3-32K-7B) ) |
|
|
|
|
|
The model recipe ended up being something I can only describe as making an omelette. Hence the model name. |
|
|
|
|
|
The models are scrambled with Dare Ties to induce a bit of randomness, then the Dare Ties merges are merged into themselves with SLERP to repair any holes cause by Dare Ties, and finally a bunch of high creativity models are thrown into the merger through merge densification(Task Arithmetic). |
|
|
|
|
|
This model uses a bunch of the top models of the UGI Leaderboard, I picked out a few of the top 8B models of each category. Most of the high creativity models in the last step were found through Lewdiculus' account uploads |
|
|
|
|
|
## Merge Method |
|
|
|
|
|
Dare Ties, SLERP, and Task Arithmetic |
|
|
|
|
|
## Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B](https://huggingface.co/Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B) |
|
|
* [bluuwhale/L3-SthenoMaidBlackroot-8B-V1](https://huggingface.co/bluuwhale/L3-SthenoMaidBlackroot-8B-V1) |
|
|
* [Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B](https://huggingface.co/Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B) |
|
|
* An unreleased Psycology merger of mine |
|
|
* [migtissera/Llama-3-8B-Synthia-v3.5](https://huggingface.co/migtissera/Llama-3-8B-Synthia-v3.5) |
|
|
* [tannedbum/L3-Nymeria-Maid-8B](https://huggingface.co/tannedbum/L3-Nymeria-Maid-8B) |
|
|
* [Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B](https://huggingface.co/Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B) |
|
|
* [ChaoticNeutrals/Hathor_RP-v.01-L3-8B](https://huggingface.co/ChaoticNeutrals/Hathor_RP-v.01-L3-8B) |
|
|
* [tannedbum/L3-Nymeria-8B](https://huggingface.co/tannedbum/L3-Nymeria-8B) |
|
|
* [Sao10K/L3-8B-Stheno-v3.1](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.1) |
|
|
* [cgato/L3-TheSpice-8b-v0.8.3](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3) |
|
|
* [ChaoticNeutrals/Poppy_Porpoise-1.4-L3-8B](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-1.4-L3-8B) |
|
|
* [ChaoticNeutrals/Hathor_RP-v.01-L3-8B](https://huggingface.co/ChaoticNeutrals/Hathor_RP-v.01-L3-8B) |
|
|
* [aifeifei798/llama3-8B-DarkIdol-1.0](https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.0) |
|
|
* [Cas-Warehouse/Llama-3-SOVL-MopeyMule-Blackroot-8B](https://huggingface.co/Cas-Warehouse/Llama-3-SOVL-MopeyMule-Blackroot-8B) |
|
|
|
|
|
# Secret Sauce |
|
|
|
|
|
The following YAML configurations was used to produce this model: |
|
|
|
|
|
## Scrambled-Egg-1 |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B |
|
|
- model: Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B |
|
|
parameters: |
|
|
density: 0.45 |
|
|
weight: 0.33 |
|
|
- model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1 |
|
|
parameters: |
|
|
density: 0.75 |
|
|
weight: 0.33 |
|
|
merge_method: dare_ties |
|
|
base_model: Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B |
|
|
parameters: |
|
|
int8_mask: true |
|
|
dtype: bfloat16 |
|
|
``` |
|
|
|
|
|
## Scrambled-Egg-2 |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: [An unreleased psychology merger of mine] |
|
|
- model: migtissera/Llama-3-8B-Synthia-v3.5 |
|
|
parameters: |
|
|
density: 0.35 |
|
|
weight: 0.25 |
|
|
- model: tannedbum/L3-Nymeria-Maid-8B |
|
|
parameters: |
|
|
density: 0.65 |
|
|
weight: 0.25 |
|
|
merge_method: dare_ties |
|
|
base_model: [An unreleased psychology merger of mine] |
|
|
parameters: |
|
|
int8_mask: true |
|
|
dtype: bfloat16 |
|
|
``` |
|
|
|
|
|
## Scrambled-Egg-3 |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B |
|
|
- model: tannedbum/L3-Nymeria-8B |
|
|
parameters: |
|
|
density: 0.5 |
|
|
weight: 0.35 |
|
|
- model: ChaoticNeutrals/Hathor_RP-v.01-L3-8B |
|
|
parameters: |
|
|
density: 0.4 |
|
|
weight: 0.2 |
|
|
merge_method: dare_ties |
|
|
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B |
|
|
parameters: |
|
|
int8_mask: true |
|
|
dtype: bfloat16 |
|
|
``` |
|
|
|
|
|
## Omelette-1 |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: Casual-Autopsy/Scrambled-Egg-1 |
|
|
- model: Casual-Autopsy/Scrambled-Egg-3 |
|
|
merge_method: slerp |
|
|
base_model: Casual-Autopsy/Scrambled-Egg-1 |
|
|
parameters: |
|
|
t: |
|
|
- value: [0.1, 0.15, 0.2, 0.4, 0.6, 0.4, 0.2, 0.15, 0.1] |
|
|
embed_slerp: true |
|
|
dtype: bfloat16 |
|
|
|
|
|
``` |
|
|
|
|
|
## Omelette-2 |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: Casual-Autopsy/Omelette-1 |
|
|
- model: Casual-Autopsy/Scrambled-Egg-2 |
|
|
merge_method: slerp |
|
|
base_model: Casual-Autopsy/Omelette-1 |
|
|
parameters: |
|
|
t: |
|
|
- value: [0.7, 0.5, 0.3, 0.25, 0.2, 0.25, 0.3, 0.5, 0.7] |
|
|
embed_slerp: true |
|
|
dtype: bfloat16 |
|
|
|
|
|
``` |
|
|
|
|
|
## L3-Uncen-Merger-Omelette-8B-EXPERIMENTAL |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: Casual-Autopsy/Omelette-2 |
|
|
- model: Cas-Warehouse/Llama-3-SOVL-MopeyMule-Blackroot-8B |
|
|
parameters: |
|
|
weight: 0.07 |
|
|
- model: ChaoticNeutrals/Hathor_RP-v.01-L3-8B |
|
|
parameters: |
|
|
weight: 0.01 |
|
|
- model: Sao10K/L3-8B-Stheno-v3.1 |
|
|
parameters: |
|
|
weight: 0.015 |
|
|
- model: aifeifei798/llama3-8B-DarkIdol-1.0 |
|
|
parameters: |
|
|
weight: 0.015 |
|
|
- model: cgato/L3-TheSpice-8b-v0.8.3 |
|
|
parameters: |
|
|
weight: 0.02 |
|
|
- model: ChaoticNeutrals/Poppy_Porpoise-1.4-L3-8B |
|
|
parameters: |
|
|
weight: 0.02 |
|
|
merge_method: task_arithmetic |
|
|
base_model: Casual-Autopsy/Omelette-2 |
|
|
dtype: bfloat16 |
|
|
``` |
