|
|
--- |
|
|
base_model: [] |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
|
|
|
--- |
|
|
# prototype-0.4x220 |
|
|
|
|
|
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 [SCE](https://arxiv.org/abs/2408.07990) merge method using /workspace/prototype-0.4x219 as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* /workspace/cache/models--ArliAI--DS-R1-Distill-70B-ArliAI-RpR-v4-Large/snapshots/f5eb02c877220331679a1ca3acfdd12e74b7304a |
|
|
* /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c |
|
|
* /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8 |
|
|
* /workspace/cache/models--Delta-Vector--Austral-70B-Winton/snapshots/c47bd9e4e8ae4151c5b26ce2ef72a95d1c15a25f |
|
|
* /workspace/cache/models--Sao10K--L3.1-70B-Hanami-x1/snapshots/f054d970fe9119d0237ce97029e6f5b9fce630eb |
|
|
* /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/0a82172eda5b6344505254fc73eea0b444f348ff |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c |
|
|
- model: /workspace/cache/models--Sao10K--L3.1-70B-Hanami-x1/snapshots/f054d970fe9119d0237ce97029e6f5b9fce630eb |
|
|
- model: /workspace/cache/models--Delta-Vector--Austral-70B-Winton/snapshots/c47bd9e4e8ae4151c5b26ce2ef72a95d1c15a25f |
|
|
- model: /workspace/cache/models--ArliAI--DS-R1-Distill-70B-ArliAI-RpR-v4-Large/snapshots/f5eb02c877220331679a1ca3acfdd12e74b7304a |
|
|
- model: /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/0a82172eda5b6344505254fc73eea0b444f348ff |
|
|
- model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8 |
|
|
base_model: /workspace/prototype-0.4x219 |
|
|
select_topk: 0.2 |
|
|
merge_method: sce |
|
|
tokenizer: |
|
|
source: base |
|
|
pad_to_multiple_of: 8 |
|
|
int8_mask: true |
|
|
dtype: bfloat16 |
|
|
``` |
|
|
|
