Instructions to use jirin/Llama-2-13b-fingpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jirin/Llama-2-13b-fingpt with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-13b-hf") model = PeftModel.from_pretrained(base_model, "jirin/Llama-2-13b-fingpt") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from jirin/Llama-2-13b-fingpt: direct link, hf CLI and curl.
- Browser
- Download file 26.3 MB
-
https://huggingface.co/jirin/Llama-2-13b-fingpt/resolve/main/adapter_model.bin
- Command line
-
hf download hf://jirin/Llama-2-13b-fingpt/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/jirin/Llama-2-13b-fingpt/resolve/main/adapter_model.bin
26.3 MB
- Xet hash:
- cc205fedbbf1aed16b44e587e11332b6dea4e8cc2cfcb9be995c3b89e1892751
- Size of remote file:
- 26.3 MB
- SHA256:
- 63d9cf8f7aaa5e33ac88eb133603076066df797bf01a9b063c6d11b4ff91c210
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.