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
14
Safetensors
Model size
631M params
Tensor type
F32
·
FP16
·
U8
·
Inference Examples
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 appvoid/palmer-003-turbo-2401