merge
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:
- ../models/uukuguy_speechless-instruct-mistral-7b-v0.2
- ../models/SanjiWatsuki_Kunoichi-DPO-v2-7B
Configuration
The following YAML configuration was used to produce this model:
models:
- model: ../models/SanjiWatsuki_Kunoichi-DPO-v2-7B
- model: ../models/uukuguy_speechless-instruct-mistral-7b-v0.2
merge_method: slerp
base_model: ../models/uukuguy_speechless-instruct-mistral-7b-v0.2
parameters:
t:
- value: [0.5, 0.1, 0.4, 0.3, 0.5, 0.7, 0.5, 0.7, 0.2, 0.1, 0.4]
embed_slerp: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.79 |
| IFEval (0-Shot) | 43.33 |
| BBH (3-Shot) | 26.91 |
| MATH Lvl 5 (4-Shot) | 5.82 |
| GPQA (0-shot) | 7.38 |
| MuSR (0-shot) | 12.29 |
| MMLU-PRO (5-shot) | 22.99 |
- Downloads last month
- 3
Model tree for Jacoby746/Proto-Harpy-Spark-v0.1-7B
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard43.330
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard26.910
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard5.820
- acc_norm on GPQA (0-shot)Open LLM Leaderboard7.380
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.290
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard22.990