Half the data was geared towards better reasoning (EvolKit-20k and reasoning-base-20k), the other half will help to de-censor the model (WizardLM data set).

Looking for GGUF?

There is a separate upload for that! Download theprint/ReWiz-Nemo-12B-Instruct-GGUF instead.

Uploaded model

  • Developed by: theprint
  • License: apache-2.0
  • Finetuned from model : unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit

This mistral 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. 15.63
IFEval (0-Shot) 10.62
BBH (3-Shot) 29.93
MATH Lvl 5 (4-Shot) 7.18
GPQA (0-shot) 9.84
MuSR (0-shot) 10.23
MMLU-PRO (5-shot) 25.99
Downloads last month
7
Safetensors
Model size
12.2B params
Tensor type
BF16
·
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 theprint/ReWiz-Nemo-12B-Instruct

Finetuned
(149)
this model
Quantizations
4 models

Collection including theprint/ReWiz-Nemo-12B-Instruct

Evaluation results