Question Answering
Transformers
Safetensors
Russian
Tatar
bert
tatar
russian
toponyms
rubert
squad
ner
geocoding
Eval Results (legacy)
Instructions to use TatarNLPWorld/rubert-large-tatar-toponyms-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TatarNLPWorld/rubert-large-tatar-toponyms-qa 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="TatarNLPWorld/rubert-large-tatar-toponyms-qa")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("TatarNLPWorld/rubert-large-tatar-toponyms-qa") model = AutoModelForQuestionAnswering.from_pretrained("TatarNLPWorld/rubert-large-tatar-toponyms-qa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from TatarNLPWorld/rubert-large-tatar-toponyms-qa: direct link, hf CLI and curl.
- Browser
- Download file 975 Bytes
-
https://huggingface.co/TatarNLPWorld/rubert-large-tatar-toponyms-qa/resolve/main/config.json
- Command line
-
hf download hf://TatarNLPWorld/rubert-large-tatar-toponyms-qa/config.json
-
curl -L -o config.json https://huggingface.co/TatarNLPWorld/rubert-large-tatar-toponyms-qa/resolve/main/config.json
975 Bytes
| { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "BertForQuestionAnswering" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": null, | |
| "classifier_dropout": null, | |
| "directionality": "bidi", | |
| "dtype": "float32", | |
| "eos_token_id": null, | |
| "finetuning_task": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "pooler_fc_size": 768, | |
| "pooler_num_attention_heads": 12, | |
| "pooler_num_fc_layers": 3, | |
| "pooler_size_per_head": 128, | |
| "pooler_type": "first_token_transform", | |
| "pruned_heads": {}, | |
| "tie_word_embeddings": true, | |
| "torchscript": false, | |
| "transformers_version": "5.3.0", | |
| "type_vocab_size": 2, | |
| "use_bfloat16": false, | |
| "use_cache": false, | |
| "vocab_size": 120138 | |
| } | |