Merges
Collection
Personal Merges
•
80 items
•
Updated
•
1
Model details:
This is definately not perfect, but it does feel pretty close.
Feedback is welcome, as always.
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 nbeerbower/Mistral-Nemo-Prism-12B 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: nbeerbower/Mistral-Nemo-Prism-12B
#no parameters necessary for base model
- model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
parameters:
density: 0.5
weight: 0.5
- model: elinas/Chronos-Gold-12B-1.0
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: nbeerbower/Mistral-Nemo-Prism-12B
parameters:
normalize: false
int8_mask: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 22.12 |
| IFEval (0-Shot) | 32.59 |
| BBH (3-Shot) | 36.58 |
| MATH Lvl 5 (4-Shot) | 11.63 |
| GPQA (0-shot) | 7.94 |
| MuSR (0-shot) | 14.28 |
| MMLU-PRO (5-shot) | 29.70 |
- Downloads last month
- 6
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/Chronos-Prism_V1.0
Merge model
this model
Collection including Triangle104/Chronos-Prism_V1.0
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard32.590
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard36.580
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard11.630
- acc_norm on GPQA (0-shot)Open LLM Leaderboard7.940
- acc_norm on MuSR (0-shot)Open LLM Leaderboard14.280
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard29.700