Merges
Collection
Personal Merges
•
104 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 SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: TheDrummer/Rocinante-12B-v1.1
- model: nbeerbower/Mistral-Nemo-Prism-12B-v2
merge_method: slerp
base_model: TheDrummer/Rocinante-12B-v1.1
dtype: bfloat16
parameters:
t: [0, 0.5, 1, 0.5, 0]
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 20.71 |
| IFEval (0-Shot) | 26.16 |
| BBH (3-Shot) | 33.23 |
| MATH Lvl 5 (4-Shot) | 10.73 |
| GPQA (0-shot) | 9.40 |
| MuSR (0-shot) | 15.42 |
| MMLU-PRO (5-shot) | 29.34 |
- Downloads last month
- 19
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Triangle104/Rocinante-Prism_V2.0
Merge model
this model
Collection including Triangle104/Rocinante-Prism_V2.0
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard26.160
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard33.230
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard10.730
- acc_norm on GPQA (0-shot)Open LLM Leaderboard9.400
- acc_norm on MuSR (0-shot)Open LLM Leaderboard15.420
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard29.340