Llama
Collection
Meta-based models
•
849 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 TIES merge method using unsloth/DeepSeek-R1-Distill-Llama-8B 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: unsloth/DeepSeek-R1-Distill-Llama-8B
#no parameters necessary for base model
- model: huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated
parameters:
density: 0.4
weight: 0.5
- model: nbeerbower/Llama3.1-Allades-8B
parameters:
density: 0.5
weight: 0.6
merge_method: ties
base_model: unsloth/DeepSeek-R1-Distill-Llama-8B
parameters:
normalize: false
int8_mask: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 22.28 |
| IFEval (0-Shot) | 34.48 |
| BBH (3-Shot) | 29.32 |
| MATH Lvl 5 (4-Shot) | 21.53 |
| GPQA (0-shot) | 10.85 |
| MuSR (0-shot) | 11.22 |
| MMLU-PRO (5-shot) | 26.30 |
- Downloads last month
- 27
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/Distilled-Whiskey-8b
Merge model
this model
Collections including Triangle104/Distilled-Whiskey-8b
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard34.480
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard29.320
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard21.530
- acc_norm on GPQA (0-shot)Open LLM Leaderboard10.850
- acc_norm on MuSR (0-shot)Open LLM Leaderboard11.220
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard26.300