personal merge highlights
Collection
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 linear merge method.
Models Merged
The following models were included in the merge:
- DreadPoor/LemonP_ALT-8B-Model_Stock
- DreadPoor/Heart_Stolen-8B-Model_Stock
- DreadPoor/Aspire_1.3-8B_model-stock + grimjim/Llama-3-Instruct-abliteration-LoRA-8B
Configuration
The following YAML configuration was used to produce this model:
models:
- model: DreadPoor/Aspire_1.3-8B_model-stock+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
parameters:
weight: 1.0
- model: DreadPoor/LemonP_ALT-8B-Model_Stock
parameters:
weight: 1.0
- model: DreadPoor/Heart_Stolen-8B-Model_Stock
parameters:
weight: 1.0
merge_method: 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 | 29.39 |
| IFEval (0-Shot) | 71.90 |
| BBH (3-Shot) | 35.01 |
| MATH Lvl 5 (4-Shot) | 16.47 |
| GPQA (0-shot) | 8.84 |
| MuSR (0-shot) | 12.93 |
| MMLU-PRO (5-shot) | 31.21 |
- Downloads last month
- 24
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for DreadPoor/Alita99-8B-LINEAR
Merge model
this model
Collection including DreadPoor/Alita99-8B-LINEAR
Evaluation results
- averaged accuracy on IFEval (0-Shot)Open LLM Leaderboard71.900
- normalized accuracy on BBH (3-Shot)test set Open LLM Leaderboard35.010
- exact match on MATH Lvl 5 (4-Shot)test set Open LLM Leaderboard16.470
- acc_norm on GPQA (0-shot)Open LLM Leaderboard8.840
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.930
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard31.210