Instructions to use MSGEncrypted/minicpm5-1b-math-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use MSGEncrypted/minicpm5-1b-math-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM5-1B") model = PeftModel.from_pretrained(base_model, "MSGEncrypted/minicpm5-1b-math-lora") - Notebooks
- Google Colab
- Kaggle
| { | |
| "gsm8k": { | |
| "before": { | |
| "n": 30, | |
| "correct": 4, | |
| "accuracy": 0.13333333333333333, | |
| "elapsed_sec": 235.86863923072815, | |
| "seed": 42 | |
| }, | |
| "after": { | |
| "n": 30, | |
| "correct": 6, | |
| "accuracy": 0.2, | |
| "elapsed_sec": 241.18271040916443, | |
| "seed": 42 | |
| } | |
| }, | |
| "piqa": { | |
| "before": { | |
| "n": 150, | |
| "correct": 93, | |
| "accuracy": 0.62, | |
| "elapsed_sec": 13.179616451263428, | |
| "seed": 42 | |
| }, | |
| "after": { | |
| "n": 150, | |
| "correct": 97, | |
| "accuracy": 0.6466666666666666, | |
| "elapsed_sec": 23.426591634750366, | |
| "seed": 42 | |
| } | |
| }, | |
| "gate_passed": true | |
| } | |