8 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 SCE merge method using FuseAI/FuseChat-Llama-3.1-8B-SFT as a base.
Models Merged
The following models were included in the merge:
- johnsutor/Llama-3-8B-Instruct_dare_ties-density-0.9
- refuelai/Llama-3-Refueled
- DreadPoor/Derivative-8B-Model_Stock
- Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
Configuration
The following YAML configuration was used to produce this model:
models:
- model: refuelai/Llama-3-Refueled
- model: johnsutor/Llama-3-8B-Instruct_dare_ties-density-0.9
- model: Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
- model: DreadPoor/Derivative-8B-Model_Stock
merge_method: sce
base_model: FuseAI/FuseChat-Llama-3.1-8B-SFT
parameters:
select_topk: 0.3
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here! Summarized results can be found here!
| Metric | Value (%) |
|---|---|
| Average | 26.62 |
| IFEval (0-Shot) | 65.15 |
| BBH (3-Shot) | 37.76 |
| MATH Lvl 5 (4-Shot) | 7.40 |
| GPQA (0-shot) | 5.03 |
| MuSR (0-shot) | 17.33 |
| MMLU-PRO (5-shot) | 27.06 |
- Downloads last month
- 3
Safetensors
Model size
8B params
Tensor type
BF16
·
Model tree for DreadPoor/Spring_Dusk-8B-SCE
Merge model
this model
Collection including DreadPoor/Spring_Dusk-8B-SCE
Paper for DreadPoor/Spring_Dusk-8B-SCE
Evaluation results
- averaged accuracy on IFEval (0-Shot)Open LLM Leaderboard65.150
- normalized accuracy on BBH (3-Shot)test set Open LLM Leaderboard37.760
- exact match on MATH Lvl 5 (4-Shot)test set Open LLM Leaderboard7.400
- acc_norm on GPQA (0-shot)Open LLM Leaderboard5.030
- acc_norm on MuSR (0-shot)Open LLM Leaderboard17.330
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard27.060