Phi
Collection
Microsoft-based models
•
136 items
•
Updated
•
1
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Roleplaying model based on Phi-4
Merge Method
This model was merged using the passthrough merge method using huihui-ai/phi-4-abliterated + bunnycore/Phi-4-RP-lora_model as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: huihui-ai/phi-4-abliterated+bunnycore/Phi-4-RP-lora_model
dtype: bfloat16
merge_method: passthrough
models:
- model: huihui-ai/phi-4-abliterated+bunnycore/Phi-4-RP-lora_model
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 37.30 |
| IFEval (0-Shot) | 49.23 |
| BBH (3-Shot) | 52.64 |
| MATH Lvl 5 (4-Shot) | 30.29 |
| GPQA (0-shot) | 19.35 |
| MuSR (0-shot) | 24.43 |
| MMLU-PRO (5-shot) | 47.86 |
- Downloads last month
- 8
Model tree for Triangle104/Phi-4-AbliteratedRP
Merge model
this model
Collections including Triangle104/Phi-4-AbliteratedRP
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard49.230
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard52.640
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard30.290
- acc_norm on GPQA (0-shot)Open LLM Leaderboard19.350
- acc_norm on MuSR (0-shot)Open LLM Leaderboard24.430
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard47.860