Tiny Fine Tunes🤏
Collection
A collection of SLM (Small Language Model) fine tunes.
•
4 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 TIES merge method using unsloth/Llama-3.2-3B-Instruct 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: NotASI/FineTome-Llama3.2-3B-1002
parameters:
weight: 1
- model: unsloth/Llama-3.2-3B-Instruct
parameters:
weight: 1
merge_method: ties
base_model: unsloth/Llama-3.2-3B-Instruct
parameters:
normalize: true
int8_mask: true
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 16.90 |
| IFEval (0-Shot) | 55.08 |
| BBH (3-Shot) | 19.46 |
| MATH Lvl 5 (4-Shot) | 5.14 |
| GPQA (0-shot) | 1.57 |
| MuSR (0-shot) | 4.07 |
| MMLU-PRO (5-shot) | 16.09 |
- Downloads last month
- 4
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 NotASI/FineTome-v1.5-Llama3.2-3B-1007
Collection including NotASI/FineTome-v1.5-Llama3.2-3B-1007
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard55.080
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard19.460
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard5.140
- acc_norm on GPQA (0-shot)Open LLM Leaderboard1.570
- acc_norm on MuSR (0-shot)Open LLM Leaderboard4.070
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard16.090