merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using DreadPoor/Rusted_Platinum-8B-LINEAR as a base.
Models Merged
The following models were included in the merge:
- SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
- DreadPoor/BaeZel-8B-LINEAR
- DreadPoor/Aspire-8B-model_stock
- DreadPoor/H_the_eighth-8B-LINEAR
Configuration
The following YAML configuration was used to produce this model:
models:
- model: DreadPoor/BaeZel-8B-LINEAR
- model: DreadPoor/H_the_eighth-8B-LINEAR
- model: SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
- model: DreadPoor/Aspire-8B-model_stock
merge_method: model_stock
base_model: DreadPoor/Rusted_Platinum-8B-LINEAR
normalize: false
int8_mask: true
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here! Summarized results can be found here!
| Metric | Value (%) |
|---|---|
| Average | 29.71 |
| IFEval (0-Shot) | 77.95 |
| BBH (3-Shot) | 32.46 |
| MATH Lvl 5 (4-Shot) | 17.07 |
| GPQA (0-shot) | 7.94 |
| MuSR (0-shot) | 11.81 |
| MMLU-PRO (5-shot) | 31.01 |
- Downloads last month
- 25
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for DreadPoor/inexpertus-8B-Model_Stock
Merge model
this model
Evaluation results
- averaged accuracy on IFEval (0-Shot)Open LLM Leaderboard77.950
- normalized accuracy on BBH (3-Shot)test set Open LLM Leaderboard32.460
- exact match on MATH Lvl 5 (4-Shot)test set Open LLM Leaderboard17.070
- acc_norm on GPQA (0-shot)Open LLM Leaderboard7.940
- acc_norm on MuSR (0-shot)Open LLM Leaderboard11.810
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard31.010