Testing Might be broken
Collection
testing only models,
•
10 items
•
Updated
•
1
This is a merge of pre-trained language models created using mergekit.
This model was merged using the task_anysize merge method using senseable/WestLake-7B-v2 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model:
model:
path: senseable/WestLake-7B-v2
dtype: bfloat16
merge_method: task_anysize
slices:
- sources:
- layer_range: [0, 32]
model:
model:
path: chargoddard/piano-medley-7b
parameters:
weight: 0.55
- layer_range: [0, 32]
model:
model:
path: senseable/WestLake-7B-v2
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 74.03 |
AI2 Reasoning Challenge (25-Shot) | 72.18 |
HellaSwag (10-Shot) | 88.52 |
MMLU (5-Shot) | 64.43 |
TruthfulQA (0-shot) | 66.72 |
Winogrande (5-shot) | 86.58 |
GSM8k (5-shot) | 65.73 |