Instructions to use AshwinKM2005/llama3-8b-dpo-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use AshwinKM2005/llama3-8b-dpo-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gpt-oss-20b") model = PeftModel.from_pretrained(base_model, "AshwinKM2005/llama3-8b-dpo-lora") - Notebooks
- Google Colab
- Kaggle
unsloth_gpt-oss-20b__proj-llama3-dpo-m2__data-trl-lib_hh-rlhf-helpful-base__beta-0.1__ebs-16__seed-42: DPO adapter upload (base: unsloth/gpt-oss-20b)
6e5550d verified - Xet hash:
- 1904036de2877074a68e99535a40a90e97ed5bb5bfcb78516b92693384419646
- Size of remote file:
- 7.06 kB
- SHA256:
- 4dcdd2595e49a3122d8914d639acf0e6919082e43c21ce14fc17b4be6435dd12
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.