Edit model card

palmer

palmer

a better base model

This model will continuosly be improved over time. The model is named as palmer-003-turbo-yearmonth formatting.

evaluation 🧪

note that this is a zero-shot setting as opposite to open llm leaderboard's few-shot evals

   Model           ARC_C   HellaSwag  PIQA  Winogrande Average
palmer-001	     | 0.2807 | 0.5524 | 0.7106 | 0.5896 | 0.5333 |
palmer-003-turbo | 0.3106 | 0.5806 | 0.7247 | 0.5951 | 0.5527 |
p-003-turbo-2401 | 0.3114 | 0.5805 | 0.7258 | 0.5959 | 0.5534 | (this)
palmer-002       | 0.3242 | 0.5956 | 0.7345 | 0.5888 | 0.5607 |

This model is as good as tinyllama base while being half the size.

prompt 📝

no prompt 🚀

Note

As of today 1/4/2024 is still not possible to convert to gguf, see more here.

Buy Me A Coffee

Downloads last month
1
Safetensors
Model size
631M params
Tensor type
F32
·
FP16
·
U8
·

Dataset used to train appvoid/palmer-003-turbo-2401