Instructions to use tagokeg/Metas-Llama2-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use tagokeg/Metas-Llama2-models with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf") model = PeftModel.from_pretrained(base_model, "tagokeg/Metas-Llama2-models") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-10/optimizer.pt from tagokeg/Metas-Llama2-models: direct link, hf CLI and curl.
- Browser
- Download file 33.7 MB
-
https://huggingface.co/tagokeg/Metas-Llama2-models/resolve/main/checkpoint-10/optimizer.pt
- Command line
-
hf download hf://tagokeg/Metas-Llama2-models/checkpoint-10/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/tagokeg/Metas-Llama2-models/resolve/main/checkpoint-10/optimizer.pt
33.7 MB
- Xet hash:
- 58934a5fd0ac0fcb48a3fc2c707846b48ee678abb5203bc39d0ac54dd0d96cff
- Size of remote file:
- 33.7 MB
- SHA256:
- 8aeb11c5dfa61162d7abd371725b6994f815a6313a4c619eccdaf8c1619e97af
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.