It's experimental, but seems fine for me, I didn't run it deeply yet but should be good for Role-play 😈 considering the two merged models, feel free to leave a suggestion or feedback.
This is a merge of pre-trained language models created using mergekit(my experimental branch swapping here )
This model was merged using the task_swapping merge method using NeuralNovel/Senzu-7B-v0.1-DPO as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: task_swapping
base_model: NeuralNovel/Senzu-7B-v0.1-DPO
models:
- model: senseable/WestLake-7B-v2
parameters:
weight: 0.75
diagonal_offset: 2 #it doesn't do anything when you use random_mask
random_mask: 0.3333
random_mask_seed: 98557
dtype: bfloat16
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 67.28 |
| AI2 Reasoning Challenge (25-Shot) | 68.34 |
| HellaSwag (10-Shot) | 85.70 |
| MMLU (5-Shot) | 64.14 |
| TruthfulQA (0-shot) | 50.43 |
| Winogrande (5-shot) | 82.48 |
| GSM8k (5-shot) | 52.62 |
model-00014-of-00041.safetensors 396 MBmodel-00041-of-00041.safetensors 394 MBmodel-00020-of-00041.safetensors 394 MBmodel-00025-of-00041.safetensors 394 MBmodel-00031-of-00041.safetensors 394 MBmodel-00036-of-00041.safetensors 394 MBmodel-00003-of-00041.safetensors 394 MBmodel-00008-of-00041.safetensors 394 MBmodel-00013-of-00041.safetensors 394 MBmodel-00019-of-00041.safetensors 394 MBmodel-00024-of-00041.safetensors 394 MBmodel-00030-of-00041.safetensors 394 MBmodel-00035-of-00041.safetensors 394 MBmodel-00040-of-00041.safetensors 394 MBmodel-00002-of-00041.safetensors 394 MBmodel-00007-of-00041.safetensors 394 MBmodel-00012-of-00041.safetensors 394 MBmodel-00015-of-00041.safetensors 386 MBmodel-00029-of-00041.safetensors 380 MBmodel-00017-of-00041.safetensors 319 MBmodel-00022-of-00041.safetensors 319 MBmodel-00027-of-00041.safetensors 319 MBmodel-00033-of-00041.safetensors 319 MBmodel-00038-of-00041.safetensors 319 MBmodel-00005-of-00041.safetensors 319 MBmodel-00010-of-00041.safetensors 319 MBmodel-00018-of-00041.safetensors 319 MBmodel-00023-of-00041.safetensors 319 MBmodel-00028-of-00041.safetensors 319 MBmodel-00034-of-00041.safetensors 319 MBmodel-00039-of-00041.safetensors 319 MBmodel-00006-of-00041.safetensors 319 MBmodel-00011-of-00041.safetensors 319 MBmodel-00016-of-00041.safetensors 319 MBmodel-00021-of-00041.safetensors 319 MBmodel-00026-of-00041.safetensors 319 MBmodel-00032-of-00041.safetensors 319 MBmodel-00037-of-00041.safetensors 319 MBmodel-00004-of-00041.safetensors 319 MBmodel-00009-of-00041.safetensors 319 MBmodel-00001-of-00041.safetensors 319 MB