TriFusionNexus-7b
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the TIES merge method using CultriX/NeuralTrix-7B-dpo 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: CultriX/NeuralTrix-7B-dpo # no parameters necessary for base model
- model: mlabonne/AlphaMonarch-7B
parameters:
density: 0.5 # fraction of weights in differences from the base model to retain
weight: # weight gradient
- filter: mlp
value: 0.5
- value: 0
- model: bardsai/jaskier-7b-dpo-v5.6
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: CultriX/NeuralTrix-7B-dpo
parameters:
normalize: true
int8_mask: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 76.32 |
| AI2 Reasoning Challenge (25-Shot) | 72.78 |
| HellaSwag (10-Shot) | 89.17 |
| MMLU (5-Shot) | 64.44 |
| TruthfulQA (0-shot) | 78.13 |
| Winogrande (5-shot) | 84.93 |
| GSM8k (5-shot) | 68.46 |
- Downloads last month
- 17
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 EryriLabs/TriFusionNexus-7b
Merge model
this model
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard72.780
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard89.170
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.440
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard78.130
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard84.930
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard68.460