Instructions to use infgrad/puff-large-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use infgrad/puff-large-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="infgrad/puff-large-v1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("infgrad/puff-large-v1") model = AutoModel.from_pretrained("infgrad/puff-large-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download 1_Pooling/config.json from infgrad/puff-large-v1: direct link, hf CLI and curl.
- Browser
- Download file 186 Bytes
-
https://huggingface.co/infgrad/puff-large-v1/resolve/main/1_Pooling/config.json
- Command line
-
hf download hf://infgrad/puff-large-v1/1_Pooling/config.json
-
curl -L -o config.json https://huggingface.co/infgrad/puff-large-v1/resolve/main/1_Pooling/config.json
186 Bytes
| { | |
| "word_embedding_dimension": 1024, | |
| "pooling_mode_cls_token": false, | |
| "pooling_mode_mean_tokens": true, | |
| "pooling_mode_max_tokens": false, | |
| "pooling_mode_mean_sqrt_len_tokens": false | |
| } |