Instructions to use c0d3r69/eptl_llama2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use c0d3r69/eptl_llama2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-chat-hf") model = PeftModel.from_pretrained(base_model, "c0d3r69/eptl_llama2") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "pad_token_id": 32000, | |
| "temperature": 0.9, | |
| "top_p": 0.6, | |
| "transformers_version": "4.31.0" | |
| } | |