merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the della merge method using Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
parameters:
weight: 1.0
- model: mlabonne/NeuralDaredevil-8B-abliterated
parameters:
weight: 1.0
base_model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
merge_method: della
parameters:
normalize: true
int8_mask: true
density: 0.7
lambda: 1.1
epsilon: 0.2
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.73 |
| IFEval (0-Shot) | 42.39 |
| BBH (3-Shot) | 28.48 |
| MATH Lvl 5 (4-Shot) | 5.74 |
| GPQA (0-shot) | 5.93 |
| MuSR (0-shot) | 8.61 |
| MMLU-PRO (5-shot) | 27.25 |
- Downloads last month
- 25
Inference API (serverless) is not available, repository is disabled.
Model tree for darkc0de/BuddyGlassNeverSleeps
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard42.390
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard28.480
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard5.740
- acc_norm on GPQA (0-shot)Open LLM Leaderboard5.930
- acc_norm on MuSR (0-shot)Open LLM Leaderboard8.610
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard27.250