Mis mezclas [Llama 3.2 - 1B]
Collection
Mezclas de los mejores modelos Llama3.2-1B existentes hasta el momento.
•
12 items
•
Updated
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: jtatman/llama-3.2-1b-lewd-mental-occult
- model: Novaciano/UNCENSORED-Sigil-Of-Satan-3.2-1B
base_model: Novaciano/UNCENSORED-Sigil-Of-Satan-3.2-1B
merge_method: slerp
dtype: bfloat16
parameters:
t: [0, 0.5, 1, 0.5, 0]
Open LLM Leaderboard Evaluation Results
Detailed results can be found here! Summarized results can be found here!
| Metric | Value (%) |
|---|---|
| Average | 12.94 |
| IFEval (0-Shot) | 52.95 |
| BBH (3-Shot) | 7.52 |
| MATH Lvl 5 (4-Shot) | 5.89 |
| GPQA (0-shot) | 1.45 |
| MuSR (0-shot) | 1.89 |
| MMLU-PRO (5-shot) | 7.93 |
- Downloads last month
- 36
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Novaciano/Cultist-3.2-1B
Merge model
this model
Collection including Novaciano/Cultist-3.2-1B
Evaluation results
- averaged accuracy on IFEval (0-Shot)Open LLM Leaderboard52.950
- normalized accuracy on BBH (3-Shot)test set Open LLM Leaderboard7.520
- exact match on MATH Lvl 5 (4-Shot)test set Open LLM Leaderboard5.890
- acc_norm on GPQA (0-shot)Open LLM Leaderboard1.450
- acc_norm on MuSR (0-shot)Open LLM Leaderboard1.890
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard7.930