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: jpacifico/Chocolatine-14B-Instruct-4k-DPO
layer_range: [0, 39]
- model: failspy/Phi-3-medium-4k-instruct-abliterated-v3
layer_range: [0, 39]
merge_method: slerp
base_model: jpacifico/Chocolatine-14B-Instruct-4k-DPO
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. | 23.53 |
| IFEval (0-Shot) | 27.01 |
| BBH (3-Shot) | 48.88 |
| MATH Lvl 5 (4-Shot) | 0.15 |
| GPQA (0-shot) | 11.74 |
| MuSR (0-shot) | 13.28 |
| MMLU-PRO (5-shot) | 40.12 |
- Downloads last month
- 14
Inference API (serverless) is not available, repository is disabled.
Model tree for allknowingroger/Ph3merge-14B
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard27.010
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard48.880
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.150
- acc_norm on GPQA (0-shot)Open LLM Leaderboard11.740
- acc_norm on MuSR (0-shot)Open LLM Leaderboard13.280
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard40.120