Working Merge in my Profile
Collection
25 items
•
Updated
•
1
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the della_linear merge method using arcee-ai/SuperNova-Medius as a base.
Models Merged
The following models were included in the merge:
- huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
- allura-org/TQ2.5-14B-Aletheia-v1
- EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
- v000000/Qwen2.5-Lumen-14B
Configuration
The following YAML configuration was used to produce this model:
merge_method: della_linear
dtype: float32
out_dtype: bfloat16
parameters:
epsilon: 0.04
lambda: 1.05
normalize: true
base_model: arcee-ai/SuperNova-Medius
tokenizer_source: arcee-ai/SuperNova-Medius
models:
- model: arcee-ai/SuperNova-Medius
parameters:
weight: 10
density: 1
- model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
parameters:
weight: 7
density: 0.5
- model: v000000/Qwen2.5-Lumen-14B
parameters:
weight: 7
density: 0.4
- model: allura-org/TQ2.5-14B-Aletheia-v1
parameters:
weight: 8
density: 0.4
- model: huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
parameters:
weight: 8
density: 0.45
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 39.96 |
| IFEval (0-Shot) | 77.96 |
| BBH (3-Shot) | 50.32 |
| MATH Lvl 5 (4-Shot) | 33.84 |
| GPQA (0-shot) | 15.77 |
| MuSR (0-shot) | 14.17 |
| MMLU-PRO (5-shot) | 47.72 |
- Downloads last month
- 38
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for djuna/Q2.5-Veltha-14B-0.5
Merge model
this model
Space using djuna/Q2.5-Veltha-14B-0.5 1
Collection including djuna/Q2.5-Veltha-14B-0.5
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard77.960
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard50.320
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard33.840
- acc_norm on GPQA (0-shot)Open LLM Leaderboard15.770
- acc_norm on MuSR (0-shot)Open LLM Leaderboard14.170
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard47.720