SauerHuatuoSkywork-o1-Llama-3.1-8B
This is a merge of pre-trained language models created using mergekit.
An experiment to hybridize a relatively high scoring Llama 3.1 8B model with o1 reasoning capabilities.
Although IFEval benched lower than the SauerkrautLM mode, every other benchmark improved from the addition of the o1 merge at low weight.
Made with Llama.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: grimjim/HuatuoSkywork-o1-Llama-3.1-8B
- model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
merge_method: slerp
base_model: grimjim/HuatuoSkywork-o1-Llama-3.1-8B
parameters:
t:
- value: 0.96
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here! Summarized results can be found here!
| Metric | Value (%) |
|---|---|
| Average | 26.63 |
| IFEval (0-Shot) | 52.19 |
| BBH (3-Shot) | 32.09 |
| MATH Lvl 5 (4-Shot) | 16.99 |
| GPQA (0-shot) | 9.51 |
| MuSR (0-shot) | 15.79 |
| MMLU-PRO (5-shot) | 33.23 |