Llama
Collection
Meta-based models
•
1203 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 passthrough merge method using cognitivecomputations/Dolphin3.0-Llama3.2-3B + bunnycore/Llama-3.2-3B-Smart-v1-lora as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: cognitivecomputations/Dolphin3.0-Llama3.2-3B+bunnycore/Llama-3.2-3B-Smart-v1-lora
dtype: bfloat16
merge_method: passthrough
models:
- model: cognitivecomputations/Dolphin3.0-Llama3.2-3B+bunnycore/Llama-3.2-3B-Smart-v1-lora
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 13.81 |
| IFEval (0-Shot) | 41.37 |
| BBH (3-Shot) | 15.35 |
| MATH Lvl 5 (4-Shot) | 2.11 |
| GPQA (0-shot) | 2.57 |
| MuSR (0-shot) | 8.15 |
| MMLU-PRO (5-shot) | 13.28 |
- Downloads last month
- 1
Model tree for Triangle104/Dolphin3-Llama3.2-Smart
Merge model
this model
Collections including Triangle104/Dolphin3-Llama3.2-Smart
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard41.370
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard15.350
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard2.110
- acc_norm on GPQA (0-shot)Open LLM Leaderboard2.570
- acc_norm on MuSR (0-shot)Open LLM Leaderboard8.150
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard13.280