FuseChat: Knowledge Fusion of Chat Models
Paper
• 2408.07990 • Published
• 14
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SCE merge method using suayptalha/Luminis-phi-4 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
# Pivot model
- model: suayptalha/Luminis-phi-4
# Target models
- model: bunnycore/Phi-4-RR-Shoup
merge_method: sce
base_model: suayptalha/Luminis-phi-4
parameters:
select_topk: 1.5
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 40.97 |
| IFEval (0-Shot) | 65.95 |
| BBH (3-Shot) | 56.07 |
| MATH Lvl 5 (4-Shot) | 48.11 |
| GPQA (0-shot) | 11.41 |
| MuSR (0-shot) | 15.11 |
| MMLU-PRO (5-shot) | 49.14 |
- Downloads last month
- 7
Model tree for bunnycore/Phi-4-Sce-exp-v0.1
Merge model
this model
Paper for bunnycore/Phi-4-Sce-exp-v0.1
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard65.950
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard56.070
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard48.110
- acc_norm on GPQA (0-shot)Open LLM Leaderboard11.410
- acc_norm on MuSR (0-shot)Open LLM Leaderboard15.110
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard49.140