Noromaid-Aeryth-7B
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: NeverSleep/Noromaid-7b-v0.2
dtype: float16
merge_method: slerp
parameters:
t:
- filter: self_attn
value: [0.22, 0.61, 0.46, 0.77, 1.0]
- filter: mlp
value: [0.78, 0.39, 0.54, 0.23, 0.0]
- value: 0.5
slices:
- sources:
- layer_range: [0, 32]
model: NeuralNovel/Aeryth-7B-v0.1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 57.82 |
| AI2 Reasoning Challenge (25-Shot) | 56.74 |
| HellaSwag (10-Shot) | 78.62 |
| MMLU (5-Shot) | 57.29 |
| TruthfulQA (0-shot) | 65.66 |
| Winogrande (5-shot) | 71.82 |
| GSM8k (5-shot) | 16.76 |
- Downloads last month
- 66
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for s3nh/Noromaid-Aeryth-7B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard56.740
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard78.620
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard57.290
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard65.660
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard71.820
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard16.760