Instructions to use cutelemonlili/Qwen2.5-32B-Instruct_lora_MATH_training_response_Qwen2.5_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cutelemonlili/Qwen2.5-32B-Instruct_lora_MATH_training_response_Qwen2.5_7B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct") model = PeftModel.from_pretrained(base_model, "cutelemonlili/Qwen2.5-32B-Instruct_lora_MATH_training_response_Qwen2.5_7B") - Notebooks
- Google Colab
- Kaggle
File size: 341 Bytes
04a19dd | 1 2 3 4 5 6 7 8 9 10 11 12 | {
"epoch": 2.0,
"eval_loss": 0.04668078199028969,
"eval_runtime": 6.46,
"eval_samples_per_second": 0.929,
"eval_steps_per_second": 0.31,
"total_flos": 678679592042496.0,
"train_loss": 0.055738416959100694,
"train_runtime": 2038.148,
"train_samples_per_second": 0.523,
"train_steps_per_second": 0.131
} |