Qwen2.5-14B
Collection
CultriX Qwen2.5-14B Models.
•
5 items
•
Updated
•
1
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using Qwen/Qwen2.5-14B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Qwen/Qwen2.5-14B-Instruct
- model: Qwen/Qwen2.5-14B
- model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.0
- model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
- model: allknowingroger/Qwenslerp2-14B
- model: allknowingroger/Qwenslerp3-14B
- model: allknowingroger/Qwen2.5-slerp-14B
- model: v000000/Qwen2.5-Lumen-14B
- model: v000000/Qwen2.5-14B-Gutenberg-1e-Delta
- model: tanliboy/lambda-qwen2.5-14b-dpo-test
base_model: Qwen/Qwen2.5-14B
merge_method: model_stock
parameters:
normalize: true
dtype: bfloat16
tokenizer_source: Qwen/Qwen2.5-14B-Instruct
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 36.39 |
IFEval (0-Shot) | 56.85 |
BBH (3-Shot) | 51.01 |
MATH Lvl 5 (4-Shot) | 27.34 |
GPQA (0-shot) | 16.44 |
MuSR (0-shot) | 17.85 |
MMLU-PRO (5-shot) | 48.84 |