| | --- |
| | base_model: |
| | - TareksLab/Amethyst-SCE-V4-LLaMa-70B |
| | - TareksLab/Emerald-SCE-V3-LLaMa-70B |
| | - TareksLab/Diamond-DL-V1-LLaMa-70B |
| | - TareksLab/Carnelian-SCE-V4-LLaMa-70B |
| | - TareksLab/Citrine-MS-V3-LLaMa-70B |
| | - TareksLab/Ruby-D-V3-LLaMa-70B |
| | library_name: transformers |
| | tags: |
| | - mergekit |
| | - merge |
| |
|
| | --- |
| | # MERGE4 |
| |
|
| | 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 [DELLA](https://arxiv.org/abs/2406.11617) merge method using [TareksLab/Diamond-DL-V1-LLaMa-70B](https://huggingface.co/TareksLab/Diamond-DL-V1-LLaMa-70B) as a base. |
| |
|
| | ### Models Merged |
| |
|
| | The following models were included in the merge: |
| | * [TareksLab/Amethyst-SCE-V4-LLaMa-70B](https://huggingface.co/TareksLab/Amethyst-SCE-V4-LLaMa-70B) |
| | * [TareksLab/Emerald-SCE-V3-LLaMa-70B](https://huggingface.co/TareksLab/Emerald-SCE-V3-LLaMa-70B) |
| | * [TareksLab/Carnelian-SCE-V4-LLaMa-70B](https://huggingface.co/TareksLab/Carnelian-SCE-V4-LLaMa-70B) |
| | * [TareksLab/Citrine-MS-V3-LLaMa-70B](https://huggingface.co/TareksLab/Citrine-MS-V3-LLaMa-70B) |
| | * [TareksLab/Ruby-D-V3-LLaMa-70B](https://huggingface.co/TareksLab/Ruby-D-V3-LLaMa-70B) |
| |
|
| | ### Configuration |
| |
|
| | The following YAML configuration was used to produce this model: |
| |
|
| | ```yaml |
| | models: |
| | - model: TareksLab/Diamond-DL-V1-LLaMa-70B |
| | parameters: |
| | weight: 0.10 |
| | density: 0.5 |
| | epsilon: 0.15 |
| | - model: TareksLab/Citrine-MS-V3-LLaMa-70B |
| | parameters: |
| | weight: [0.35, 0.25, 0.17, 0.12, 0.11] |
| | density: 0.5 |
| | epsilon: 0.15 |
| | - model: TareksLab/Amethyst-SCE-V4-LLaMa-70B |
| | parameters: |
| | weight: [0.24, 0.27, 0.2, 0.16, 0.13] |
| | density: 0.5 |
| | epsilon: 0.15 |
| | - model: TareksLab/Ruby-D-V3-LLaMa-70B |
| | parameters: |
| | weight: [0.17, 0.2, 0.26, 0.2, 0.17] |
| | density: 0.5 |
| | epsilon: 0.15 |
| | - model: TareksLab/Carnelian-SCE-V4-LLaMa-70B |
| | parameters: |
| | weight: [0.13, 0.16, 0.2, 0.27, 0.24] |
| | density: 0.5 |
| | epsilon: 0.15 |
| | - model: TareksLab/Emerald-SCE-V3-LLaMa-70B |
| | parameters: |
| | weight: [0.11, 0.12, 0.17, 0.25, 0.35] |
| | density: 0.5 |
| | epsilon: 0.15 |
| | merge_method: della |
| | base_model: TareksLab/Diamond-DL-V1-LLaMa-70B |
| | parameters: |
| | lambda: 1.1 |
| | normalize: false |
| | dtype: float32 |
| | out_dtype: bfloat16 |
| | chat_template: llama3 |
| | tokenizer: |
| | source: TareksLab/Ruby-D-V3-LLaMa-70B |
| | pad_to_multiple_of: 8 |
| | |
| | ``` |
| |
|
