Instructions to use fufuf/llama2-riz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use fufuf/llama2-riz with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("TinyPixel/Llama-2-7B-bf16-sharded") model = PeftModel.from_pretrained(base_model, "fufuf/llama2-riz") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 293918a3830d49ca2e77ff5aa4d2298f1191e55d6c2fa844bc09e7ca909d1585
- Size of remote file:
- 134 MB
- SHA256:
- 501111002830b41ac37e9451173f2270cb9b31c8aae8dcee8f8e52ce4425325b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.