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
Download eval_results.json from andstor/Qwen-Qwen2.5-Coder-7B-unit-test-lora: direct link, hf CLI and curl.
- Browser
- Download file 281 Bytes
-
https://huggingface.co/andstor/Qwen-Qwen2.5-Coder-7B-unit-test-lora/resolve/main/eval_results.json
- Command line
-
hf download hf://andstor/Qwen-Qwen2.5-Coder-7B-unit-test-lora/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/andstor/Qwen-Qwen2.5-Coder-7B-unit-test-lora/resolve/main/eval_results.json
281 Bytes
| { | |
| "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 | |
| } |