Instructions to use monsterapi/llama2_70B_dolly15k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use monsterapi/llama2_70B_dolly15k with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-70b-hf") model = PeftModel.from_pretrained(base_model, "monsterapi/llama2_70B_dolly15k") - Notebooks
- Google Colab
- Kaggle
Download train-loss.png from monsterapi/llama2_70B_dolly15k: direct link, hf CLI and curl.
- Browser
- Download file 1.36 MB
-
https://huggingface.co/monsterapi/llama2_70B_dolly15k/resolve/main/train-loss.png
- Command line
-
hf download hf://monsterapi/llama2_70B_dolly15k/train-loss.png
-
curl -L -o train-loss.png https://huggingface.co/monsterapi/llama2_70B_dolly15k/resolve/main/train-loss.png
1.36 MB

- Xet hash:
- 57e0379b994831a8c7113c89a2605e8f2adc7455bef48b8e1c31a639bdd06220
- Size of remote file:
- 1.36 MB
- SHA256:
- 96de8bbfa4d9abe16fc72164ad21a6fc39c9d7f5886cbe5c490c2175d0da2e95
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.