Instructions to use andstor/Qwen-Qwen2.5-Coder-7B-unit-test-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use andstor/Qwen-Qwen2.5-Coder-7B-unit-test-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-7B") model = PeftModel.from_pretrained(base_model, "andstor/Qwen-Qwen2.5-Coder-7B-unit-test-lora") - Notebooks
- Google Colab
- Kaggle
File size: 281 Bytes
57953ae | 1 2 3 4 5 6 7 8 9 10 | {
"epoch": 2.9983597594313833,
"eval_accuracy": 0.7330547493071854,
"eval_loss": 0.7556940317153931,
"eval_runtime": 26.4169,
"eval_samples": 934,
"eval_samples_per_second": 35.356,
"eval_steps_per_second": 17.678,
"perplexity": 2.1290886657630894
} |