Instructions to use keisuke-miyako/bge-m3-doc-r3-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use keisuke-miyako/bge-m3-doc-r3-adapter with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("keisuke-miyako/bge-m3-doc-R2-merged") model = PeftModel.from_pretrained(base_model, "keisuke-miyako/bge-m3-doc-r3-adapter") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from keisuke-miyako/bge-m3-doc-r3-adapter: direct link, hf CLI and curl.
- Browser
- Download file 17.1 MB
-
https://huggingface.co/keisuke-miyako/bge-m3-doc-r3-adapter/resolve/main/tokenizer.json
- Command line
-
hf download hf://keisuke-miyako/bge-m3-doc-r3-adapter/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/keisuke-miyako/bge-m3-doc-r3-adapter/resolve/main/tokenizer.json
17.1 MB
- Xet hash:
- 73a563baf68d51e5cf2e28fc8a7d5887633303c074a7029c1fdcd02a0c8ef954
- Size of remote file:
- 17.1 MB
- SHA256:
- e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.