Instructions to use SamChen888/Gemma-RDE-Finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SamChen888/Gemma-RDE-Finetuned with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-2-9b-it-bnb-4bit") model = PeftModel.from_pretrained(base_model, "SamChen888/Gemma-RDE-Finetuned") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download train_results.json from SamChen888/Gemma-RDE-Finetuned: direct link, hf CLI and curl.
- Browser
- Download file 225 Bytes
-
https://huggingface.co/SamChen888/Gemma-RDE-Finetuned/resolve/main/train_results.json
- Command line
-
hf download hf://SamChen888/Gemma-RDE-Finetuned/train_results.json
-
curl -L -o train_results.json https://huggingface.co/SamChen888/Gemma-RDE-Finetuned/resolve/main/train_results.json
225 Bytes
| { | |
| "epoch": 2.9935483870967743, | |
| "total_flos": 1.8445406605964083e+17, | |
| "train_loss": 0.07509650238629045, | |
| "train_runtime": 10732.2973, | |
| "train_samples_per_second": 1.039, | |
| "train_steps_per_second": 0.032 | |
| } |