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 Sao10K/L3-8B-Stheno-v3.2 as a base.
Models Merged
The following models were included in the merge:
- refuelai/Llama-3-Refueled
- cognitivecomputations/dolphin-2.9-llama3-8b
- NousResearch/Hermes-2-Theta-Llama-3-8B
- NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
- cgato/L3-TheSpice-8b-v0.8.3
Configuration
The following YAML configuration was used to produce this model:
models:
- model: refuelai/Llama-3-Refueled
- model: cognitivecomputations/dolphin-2.9-llama3-8b
- model: cgato/L3-TheSpice-8b-v0.8.3
- model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
- model: NousResearch/Hermes-2-Theta-Llama-3-8B
merge_method: model_stock
base_model: Sao10K/L3-8B-Stheno-v3.2
normalize: false
int8_mask: true
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 26.78 |
| IFEval (0-Shot) | 67.86 |
| BBH (3-Shot) | 36.41 |
| MATH Lvl 5 (4-Shot) | 9.21 |
| GPQA (0-shot) | 7.38 |
| MuSR (0-shot) | 10.97 |
| MMLU-PRO (5-shot) | 28.87 |
- Downloads last month
- 34
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/ONeil-model_stock-8B
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard67.860
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard36.410
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard9.210
- acc_norm on GPQA (0-shot)Open LLM Leaderboard7.380
- acc_norm on MuSR (0-shot)Open LLM Leaderboard10.970
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard28.870