mergellama
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the task arithmetic merge method using meta-llama/Meta-Llama-3.1-8B-Instruct as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: meta-llama/Meta-Llama-3-8B-Instruct
parameters:
weight: 0.2
- model: meta-llama/Meta-Llama-3.1-8B-Instruct
parameters:
weight: 0.8
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
merge_method: task_arithmetic
parameters:
normalize: true
int8_mask: true
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 24.26 |
| IFEval (0-Shot) | 74.03 |
| BBH (3-Shot) | 28.41 |
| MATH Lvl 5 (4-Shot) | 8.53 |
| GPQA (0-shot) | 0.78 |
| MuSR (0-shot) | 4.65 |
| MMLU-PRO (5-shot) | 29.17 |
- Downloads last month
- 26
Inference API (serverless) is not available, repository is disabled.
Model tree for UKzExecution/LlamaExecutor-8B-3.0.5
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard74.030
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard28.410
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard8.530
- acc_norm on GPQA (0-shot)Open LLM Leaderboard0.780
- acc_norm on MuSR (0-shot)Open LLM Leaderboard4.650
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard29.170