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.

This model has been fine tuned for 1 epoch on the CleverBoi-Data-20k data set.

Uploaded model

Developed by: theprint
License: apache-2.0
Finetuned from model : unsloth/meta-llama-3.1-8b-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.	14.01
IFEval (0-Shot)	19.61
BBH (3-Shot)	24.13
MATH Lvl 5 (4-Shot)	4.46
GPQA (0-shot)	4.81
MuSR (0-shot)	6.72
MMLU-PRO (5-shot)	24.31

Downloads last month: 130

Safetensors

Model size

8.03B params

Tensor type

BF16

Inference Examples

Text Generation

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.

Dataset used to train theprint/CleverBoi-Llama-3.1-8B-v2

Collection including theprint/CleverBoi-Llama-3.1-8B-v2

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 Oct 7 • 1

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

19.610
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

24.130
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

4.460
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

4.810
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

6.720
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

24.310

View on Papers With Code