|
--- |
|
base_model: |
|
- nbeerbower/llama-3-stella-8B |
|
- nbeerbower/llama-3-dragonmaid-8B |
|
- nbeerbower/llama-3-sauce-v1-8B |
|
- nbeerbower/llama3.1-cc-8B |
|
- nbeerbower/Llama3.1-Allades-8B |
|
- nbeerbower/llama-3-sauce-v2-8B |
|
- nbeerbower/llama-3-gutenberg-8B |
|
- nbeerbower/llama-3-spicy-abliterated-stella-8B |
|
- nbeerbower/llama3-KawaiiMahouSauce-8B |
|
- nbeerbower/llama-3-spicy-8B |
|
- nbeerbower/llama-3-stinky-v2-8B |
|
- nbeerbower/llama-3-Stheno-Mahou-8B |
|
- nbeerbower/llama-3-dragonmaid-8B-v2 |
|
- nbeerbower/llama-3-SNAMD-8B |
|
- nbeerbower/llama-3-stinky-8B |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# 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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [MrRobotoAI/10](https://huggingface.co/MrRobotoAI/10) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [nbeerbower/llama-3-stella-8B](https://huggingface.co/nbeerbower/llama-3-stella-8B) |
|
* [nbeerbower/llama-3-dragonmaid-8B](https://huggingface.co/nbeerbower/llama-3-dragonmaid-8B) |
|
* [nbeerbower/llama-3-sauce-v1-8B](https://huggingface.co/nbeerbower/llama-3-sauce-v1-8B) |
|
* [nbeerbower/llama3.1-cc-8B](https://huggingface.co/nbeerbower/llama3.1-cc-8B) |
|
* [nbeerbower/Llama3.1-Allades-8B](https://huggingface.co/nbeerbower/Llama3.1-Allades-8B) |
|
* [nbeerbower/llama-3-sauce-v2-8B](https://huggingface.co/nbeerbower/llama-3-sauce-v2-8B) |
|
* [nbeerbower/llama-3-gutenberg-8B](https://huggingface.co/nbeerbower/llama-3-gutenberg-8B) |
|
* [nbeerbower/llama3-KawaiiMahouSauce-8B](https://huggingface.co/nbeerbower/llama3-KawaiiMahouSauce-8B) |
|
* [nbeerbower/llama-3-spicy-abliterated-stella-8B](https://huggingface.co/nbeerbower/llama-3-spicy-abliterated-stella-8B) |
|
* [nbeerbower/llama-3-spicy-8B](https://huggingface.co/nbeerbower/llama-3-spicy-8B) |
|
* [nbeerbower/llama-3-stinky-v2-8B](https://huggingface.co/nbeerbower/llama-3-stinky-v2-8B) |
|
* [nbeerbower/llama-3-Stheno-Mahou-8B](https://huggingface.co/nbeerbower/llama-3-Stheno-Mahou-8B) |
|
* [nbeerbower/llama-3-dragonmaid-8B-v2](https://huggingface.co/nbeerbower/llama-3-dragonmaid-8B-v2) |
|
* [nbeerbower/llama-3-SNAMD-8B](https://huggingface.co/nbeerbower/llama-3-SNAMD-8B) |
|
* [nbeerbower/llama-3-stinky-8B](https://huggingface.co/nbeerbower/llama-3-stinky-8B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: nbeerbower/llama-3-gutenberg-8B |
|
- model: nbeerbower/Llama3.1-Allades-8B |
|
- model: nbeerbower/llama3.1-cc-8B |
|
- model: nbeerbower/llama-3-SNAMD-8B |
|
- model: nbeerbower/llama-3-Stheno-Mahou-8B |
|
- model: nbeerbower/llama-3-stinky-v2-8B |
|
- model: nbeerbower/llama-3-sauce-v2-8B |
|
- model: nbeerbower/llama3-KawaiiMahouSauce-8B |
|
- model: nbeerbower/nbeerbower/llama-3-spicy-abliterated-stella-8B |
|
- model: nbeerbower/llama-3-spicy-8B |
|
- model: nbeerbower/llama-3-stella-8B |
|
- model: nbeerbower/llama-3-dragonmaid-8B-v2 |
|
- model: nbeerbower/llama-3-stinky-8B |
|
- model: nbeerbower/llama-3-dragonmaid-8B |
|
- model: nbeerbower/llama-3-sauce-v1-8B |
|
merge_method: model_stock |
|
base_model: MrRobotoAI/10 |
|
normalize: false |
|
dtype: float16 |
|
``` |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
merge_method: dare_linear |
|
models: |
|
- model: MrRobotoAI/10 |
|
parameters: |
|
weight: |
|
- filter: v_proj |
|
value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8] |
|
- filter: o_proj |
|
value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8] |
|
- filter: up_proj |
|
value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8] |
|
- filter: gate_proj |
|
value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8] |
|
- filter: down_proj |
|
value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8] |
|
- value: 1 |
|
- model: MrRobotoAI/NBeerbower-ConversationalMix-8b |
|
parameters: |
|
weight: |
|
- filter: v_proj |
|
value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2] |
|
- filter: o_proj |
|
value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2] |
|
- filter: up_proj |
|
value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2] |
|
- filter: gate_proj |
|
value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2] |
|
- filter: down_proj |
|
value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2] |
|
- value: 0 |
|
base_model: MrRobotoAI/10 |
|
tokenizer_source: base |
|
dtype: bfloat16 |
|
``` |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jspr/smut_llama_8b_smut_2k_romance_1k_peft](https://huggingface.co/jspr/smut_llama_8b_smut_2k_romance_1k_peft) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [kik41/lora-sarcasm-more-llama-3-8b-v2](https://huggingface.co/kik41/lora-sarcasm-more-llama-3-8b-v2) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jeiku/Writing_Mistral](https://huggingface.co/jeiku/Writing_Mistral) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jspr/llama3-instruct-wordcel-smutrom-8k_peft](https://huggingface.co/jspr/llama3-instruct-wordcel-smutrom-8k_peft) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [ResplendentAI/Luna_Llama3](https://huggingface.co/ResplendentAI/Luna_Llama3) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [Azazelle/Llama-3-Sunfall-8b-lora](https://huggingface.co/Azazelle/Llama-3-Sunfall-8b-lora) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jeiku/Synthetic_Soul_1k_Mistral_128](https://huggingface.co/jeiku/Synthetic_Soul_1k_Mistral_128) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jeiku/Futadom_Mistral](https://huggingface.co/jeiku/Futadom_Mistral) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [kik41/lora-type-descriptive-llama-3-8b-v2](https://huggingface.co/kik41/lora-type-descriptive-llama-3-8b-v2) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [ResplendentAI/BlueMoon_Llama3](https://huggingface.co/ResplendentAI/BlueMoon_Llama3) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jrahn/llama-3-8b-claudstruct-v3](https://huggingface.co/jrahn/llama-3-8b-claudstruct-v3) |
|
* [nothingiisreal/L3-8B-Stheno-Horny-v3.3-32K](https://huggingface.co/nothingiisreal/L3-8B-Stheno-Horny-v3.3-32K) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [kik41/lora-type-narrative-llama-3-8b-v2](https://huggingface.co/kik41/lora-type-narrative-llama-3-8b-v2) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [kromcomp/L3-Unaligned-r256-LoRA](https://huggingface.co/kromcomp/L3-Unaligned-r256-LoRA) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [WebNovelTrans/bEn0Kxa3dhCP8PCn](https://huggingface.co/WebNovelTrans/bEn0Kxa3dhCP8PCn) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [vincentyandex/lora_llama3_chunked_novel_bs128](https://huggingface.co/vincentyandex/lora_llama3_chunked_novel_bs128) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [ResplendentAI/Llama3_RP_ORPO_LoRA](https://huggingface.co/ResplendentAI/Llama3_RP_ORPO_LoRA) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [Triangle104/Vulkane_120-Days-of-Sodom-LoRA-Mistral-7b](https://huggingface.co/Triangle104/Vulkane_120-Days-of-Sodom-LoRA-Mistral-7b) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jeiku/Sissification_Hypno_Mistral](https://huggingface.co/jeiku/Sissification_Hypno_Mistral) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [vaitech/open-hermes-erotic-story-finetune](https://huggingface.co/vaitech/open-hermes-erotic-story-finetune) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jeiku/Humiliation_Mistral](https://huggingface.co/jeiku/Humiliation_Mistral) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jeiku/NSFW_Niche_Mistral](https://huggingface.co/jeiku/NSFW_Niche_Mistral) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [Azazelle/Nimue-8B](https://huggingface.co/Azazelle/Nimue-8B) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jspr/smut_llama_8b_smutromance_32k_peft](https://huggingface.co/jspr/smut_llama_8b_smutromance_32k_peft) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [ResplendentAI/Theory_of_Mind_Llama3](https://huggingface.co/ResplendentAI/Theory_of_Mind_Llama3) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [lemonilia/ShoriRP-v0.75d](https://huggingface.co/lemonilia/ShoriRP-v0.75d) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [nothingiisreal/llama3-8B-DWP-lora](https://huggingface.co/nothingiisreal/llama3-8B-DWP-lora) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [kik41/lora-type-persuasive-llama-3-8b-v2](https://huggingface.co/kik41/lora-type-persuasive-llama-3-8b-v2) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [kik41/lora-formality-informal-llama-3-8b-v2](https://huggingface.co/kik41/lora-formality-informal-llama-3-8b-v2) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [ResplendentAI/Aura_Llama3](https://huggingface.co/ResplendentAI/Aura_Llama3) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [mpasila/Llama-3.1-Literotica-LoRA-8B](https://huggingface.co/mpasila/Llama-3.1-Literotica-LoRA-8B) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [ResplendentAI/NoWarning_Llama3](https://huggingface.co/ResplendentAI/NoWarning_Llama3) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jspr/llama3-instruct-wordcel-smutrom_peft](https://huggingface.co/jspr/llama3-instruct-wordcel-smutrom_peft) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jspr/llama3-wordcel-smutrom-reorder_peft](https://huggingface.co/jspr/llama3-wordcel-smutrom-reorder_peft) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jeiku/Alpaca_NSFW_Shuffled_Mistral](https://huggingface.co/jeiku/Alpaca_NSFW_Shuffled_Mistral) |
|
* [MrRobotoAI/2](https://huggingface.co/MrRobotoAI/2) + [jspr/llama3-wordcel-smutrom_peft](https://huggingface.co/jspr/llama3-wordcel-smutrom_peft) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: MrRobotoAI/2+Azazelle/Llama-3-Sunfall-8b-lora |
|
- model: MrRobotoAI/2+Azazelle/Nimue-8B |
|
- model: MrRobotoAI/2+jeiku/Alpaca_NSFW_Shuffled_Mistral |
|
- model: MrRobotoAI/2+jeiku/Futadom_Mistral |
|
- model: MrRobotoAI/2+jeiku/Humiliation_Mistral |
|
- model: MrRobotoAI/2+jeiku/NSFW_Niche_Mistral |
|
- model: MrRobotoAI/2+jeiku/Sissification_Hypno_Mistral |
|
- model: MrRobotoAI/2+jeiku/Synthetic_Soul_1k_Mistral_128 |
|
- model: MrRobotoAI/2+jeiku/Writing_Mistral |
|
- model: MrRobotoAI/2+jrahn/llama-3-8b-claudstruct-v3 |
|
- model: MrRobotoAI/2+jspr/llama3-instruct-wordcel-smutrom_peft |
|
- model: MrRobotoAI/2+jspr/llama3-instruct-wordcel-smutrom-8k_peft |
|
- model: MrRobotoAI/2+jspr/llama3-wordcel-smutrom_peft |
|
- model: MrRobotoAI/2+jspr/llama3-wordcel-smutrom-reorder_peft |
|
- model: MrRobotoAI/2+jspr/smut_llama_8b_smut_2k_romance_1k_peft |
|
- model: MrRobotoAI/2+jspr/smut_llama_8b_smutromance_32k_peft |
|
- model: MrRobotoAI/2+kik41/lora-formality-informal-llama-3-8b-v2 |
|
- model: MrRobotoAI/2+kik41/lora-sarcasm-more-llama-3-8b-v2 |
|
- model: MrRobotoAI/2+kik41/lora-type-descriptive-llama-3-8b-v2 |
|
- model: MrRobotoAI/2+kik41/lora-type-narrative-llama-3-8b-v2 |
|
- model: MrRobotoAI/2+kik41/lora-type-persuasive-llama-3-8b-v2 |
|
- model: MrRobotoAI/2+kromcomp/L3-Unaligned-r256-LoRA |
|
- model: MrRobotoAI/2+lemonilia/ShoriRP-v0.75d |
|
- model: MrRobotoAI/2+mpasila/Llama-3.1-Literotica-LoRA-8B |
|
- model: MrRobotoAI/2+nothingiisreal/llama3-8B-DWP-lora |
|
- model: MrRobotoAI/2+ResplendentAI/Aura_Llama3 |
|
- model: MrRobotoAI/2+ResplendentAI/BlueMoon_Llama3 |
|
- model: MrRobotoAI/2+ResplendentAI/Llama3_RP_ORPO_LoRA |
|
- model: MrRobotoAI/2+ResplendentAI/Luna_Llama3 |
|
- model: MrRobotoAI/2+ResplendentAI/NoWarning_Llama3 |
|
- model: MrRobotoAI/2+ResplendentAI/Theory_of_Mind_Llama3 |
|
- model: MrRobotoAI/2+Triangle104/Vulkane_120-Days-of-Sodom-LoRA-Mistral-7b |
|
- model: MrRobotoAI/2+vaitech/open-hermes-erotic-story-finetune |
|
- model: MrRobotoAI/2+vincentyandex/lora_llama3_chunked_novel_bs128 |
|
- model: MrRobotoAI/2+WebNovelTrans/bEn0Kxa3dhCP8PCn |
|
- model: nothingiisreal/L3-8B-Stheno-Horny-v3.3-32K |
|
merge_method: model_stock |
|
base_model: MrRobotoAI/10 |
|
normalize: false |
|
dtype: float16 |
|
``` |
|
|
