Instructions to use tau/splinter-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tau/splinter-base with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="tau/splinter-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("tau/splinter-base") model = AutoModelForQuestionAnswering.from_pretrained("tau/splinter-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from tau/splinter-base: direct link, hf CLI and curl.
- Browser
- Download file 450 Bytes
-
https://huggingface.co/tau/splinter-base/resolve/main/config.json
- Command line
-
hf download hf://tau/splinter-base/config.json
-
curl -L -o config.json https://huggingface.co/tau/splinter-base/resolve/main/config.json
450 Bytes
| { | |
| "architectures": [ | |
| "SplinterForQuestionAnswering" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "splinter", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "type_vocab_size": 2, | |
| "vocab_size": 28996 | |
| } | |