Qwen
Collection
Alibaba Cloud-based models
•
2186 items
•
Updated
•
5
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Quant: https://huggingface.co/Triangle104/Q2.5-AthensCOT-Q4_K_M-GGUF
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: Spestly/Athena-1-7B
- model: prithivMLmods/QwQ-LCoT2-7B-Instruct
merge_method: slerp
base_model: Spestly/Athena-1-7B
dtype: bfloat16
parameters:
t: [0, 0.5, 1, 0.5, 0]
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 27.36 |
| IFEval (0-Shot) | 45.73 |
| BBH (3-Shot) | 36.45 |
| MATH Lvl 5 (4-Shot) | 21.98 |
| GPQA (0-shot) | 6.71 |
| MuSR (0-shot) | 15.76 |
| MMLU-PRO (5-shot) | 37.55 |
- Downloads last month
- 2
Model tree for Triangle104/Q2.5-AthensCOT
Merge model
this model
Collections including Triangle104/Q2.5-AthensCOT
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard45.730
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard36.450
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard21.980
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.710
- acc_norm on MuSR (0-shot)Open LLM Leaderboard15.760
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard37.550