CleverBoi
Collection
CleverBoi is a curated collection of data that emphasizes logic, inference, science, code, math and empathy, and its fine tuned language models.
•
16 items
•
Updated
•
1
CleverBoi
The CleverBoi series is based on models that have been fine tuned on a collection of data sets that emphasize logic, inference, math and coding, also known as the CleverBoi data set.
Uploaded model
- Developed by: theprint
- License: apache-2.0
- Finetuned from model : unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 13.55 |
| IFEval (0-Shot) | 16.82 |
| BBH (3-Shot) | 24.05 |
| MATH Lvl 5 (4-Shot) | 2.42 |
| GPQA (0-shot) | 6.71 |
| MuSR (0-shot) | 8.28 |
| MMLU-PRO (5-shot) | 23.06 |
- Downloads last month
- 965
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for theprint/CleverBoi-Llama-3.1-8B-Instruct
Base model
unsloth/Meta-Llama-3.1-8BDataset used to train theprint/CleverBoi-Llama-3.1-8B-Instruct
Collection including theprint/CleverBoi-Llama-3.1-8B-Instruct
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard16.820
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard24.050
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard2.420
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.710
- acc_norm on MuSR (0-shot)Open LLM Leaderboard8.280
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard23.060