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:
slices:
- sources:
- model: failspy/Phi-3-medium-4k-instruct-abliterated-v3
layer_range: [0, 39]
- model: dnhkng/RYS-Phi-3-medium-4k-instruct
layer_range: [0, 39]
merge_method: slerp
base_model: failspy/Phi-3-medium-4k-instruct-abliterated-v3
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 7.93 |
| IFEval (0-Shot) | 16.45 |
| BBH (3-Shot) | 10.39 |
| MATH Lvl 5 (4-Shot) | 0.00 |
| GPQA (0-shot) | 4.70 |
| MuSR (0-shot) | 8.86 |
| MMLU-PRO (5-shot) | 7.19 |
- Downloads last month
- 18
Inference API (serverless) is not available, repository is disabled.
Model tree for allknowingroger/Ph3merge3-14B
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard16.450
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard10.390
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard4.700
- acc_norm on MuSR (0-shot)Open LLM Leaderboard8.860
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard7.190