Qwen
Collection
Alibaba Cloud-based models
•
1040 items
•
Updated
•
3
merge
This is a merge of pre-trained language models created using mergekit.
Merge Method
This model was merged using the TIES merge method using Qwen/Qwen2.5-14B-Instruct-1M 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: huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated
parameters:
density: 1
weight: 1
- model: Qwen/Qwen2.5-14B-Instruct-1M
parameters:
density: 1
weight: 1
merge_method: ties
base_model: Qwen/Qwen2.5-14B-Instruct-1M
parameters:
normalize: false
int8_mask: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 37.41 |
| IFEval (0-Shot) | 59.86 |
| BBH (3-Shot) | 47.26 |
| MATH Lvl 5 (4-Shot) | 35.73 |
| GPQA (0-shot) | 16.67 |
| MuSR (0-shot) | 19.68 |
| MMLU-PRO (5-shot) | 45.28 |
- Downloads last month
- 20
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 Triangle104/Q2.5-14B-Instruct-1M-Harmony
Merge model
this model
Collection including Triangle104/Q2.5-14B-Instruct-1M-Harmony
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard59.860
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard47.260
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard35.730
- acc_norm on GPQA (0-shot)Open LLM Leaderboard16.670
- acc_norm on MuSR (0-shot)Open LLM Leaderboard19.680
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard45.280