Merged Models
Collection
Using mergekit
•
10 items
•
Updated
•
2
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 )
Merge Details
Merge Method
This model was merged using the task_swapping merge method using NeuralNovel/Senzu-7B-v0.1-DPO as a base.
Models Merged
The following models were included in the merge:
Configuration
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
Open LLM Leaderboard Evaluation Results
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 |
- Downloads last month
- 2,852
Merge of
Collection including Aryanne/WestSenzu-Swap-7B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard68.340
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.700
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.140
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard50.430
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard82.480
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard52.620