Instructions to use dreaming-tree/tmp_trainer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dreaming-tree/tmp_trainer with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, RobertaTaggerForMultiSpanQA tokenizer = AutoTokenizer.from_pretrained("dreaming-tree/tmp_trainer") model = RobertaTaggerForMultiSpanQA.from_pretrained("dreaming-tree/tmp_trainer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from dreaming-tree/tmp_trainer: direct link, hf CLI and curl.
- Browser
- Download file 2.24 GB
-
https://huggingface.co/dreaming-tree/tmp_trainer/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://dreaming-tree/tmp_trainer/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/dreaming-tree/tmp_trainer/resolve/main/pytorch_model.bin
2.24 GB
- Xet hash:
- a55d7e7b3a54765d407173834140e40bc77fcce0d0efb15987d942aa162586ae
- Size of remote file:
- 2.24 GB
- SHA256:
- 99b7887fc196f34c043e1acc0bb2706f898567bd97bf63d3da4162757110c812
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.