Llama
Collection
Meta-based models
•
854 items
•
Updated
•
1
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 allura-org/L3.1-8b-RP-Ink 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: allura-org/L3.1-8b-RP-Ink
parameters:
density: 0.5
weight: 0.5
- model: SicariusSicariiStuff/Dusk_Rainbow
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: allura-org/L3.1-8b-RP-Ink
parameters:
normalize: false
int8_mask: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 22.35 |
| IFEval (0-Shot) | 45.30 |
| BBH (3-Shot) | 30.51 |
| MATH Lvl 5 (4-Shot) | 12.08 |
| GPQA (0-shot) | 5.26 |
| MuSR (0-shot) | 11.17 |
| MMLU-PRO (5-shot) | 29.81 |
- Downloads last month
- 37
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/L3.1-8B-Dusky-Ink
Merge model
this model
Collections including Triangle104/L3.1-8B-Dusky-Ink
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard45.300
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard30.510
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard12.080
- acc_norm on GPQA (0-shot)Open LLM Leaderboard5.260
- acc_norm on MuSR (0-shot)Open LLM Leaderboard11.170
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard29.810