personal merge highlights
Collection
8 items
•
Updated
•
1
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the linear merge method.
Models Merged
The following models were included in the merge:
- DreadPoor/Heart_Stolen-8B-Model_Stock
- DreadPoor/Aspire_1.3-8B_model-stock
- DreadPoor/LemonP-8B-Model_Stock
Configuration
The following YAML configuration was used to produce this model:
models:
- model: DreadPoor/Aspire_1.3-8B_model-stock
parameters:
weight: 1.0
- model: DreadPoor/LemonP-8B-Model_Stock
parameters:
weight: 1.0
- model: DreadPoor/Heart_Stolen-8B-Model_Stock
parameters:
weight: 1.0
merge_method: linear
normalize: false
int8_mask: true
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 30.30 |
| IFEval (0-Shot) | 73.78 |
| BBH (3-Shot) | 35.54 |
| MATH Lvl 5 (4-Shot) | 17.82 |
| GPQA (0-shot) | 9.51 |
| MuSR (0-shot) | 13.34 |
| MMLU-PRO (5-shot) | 31.79 |
- Downloads last month
- 103
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 DreadPoor/BaeZel-8B-LINEAR
Merge model
this model
Collection including DreadPoor/BaeZel-8B-LINEAR
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard73.780
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard35.540
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard17.820
- acc_norm on GPQA (0-shot)Open LLM Leaderboard9.510
- acc_norm on MuSR (0-shot)Open LLM Leaderboard13.340
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard31.790