Instructions to use kiyoung2/koelectra-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kiyoung2/koelectra-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="kiyoung2/koelectra-small")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("kiyoung2/koelectra-small") model = AutoModelForQuestionAnswering.from_pretrained("kiyoung2/koelectra-small", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from kiyoung2/koelectra-small: direct link, hf CLI and curl.
- Browser
- Download file 853 Bytes
-
https://huggingface.co/kiyoung2/koelectra-small/resolve/main/config.json
- Command line
-
hf download hf://kiyoung2/koelectra-small/config.json
-
curl -L -o config.json https://huggingface.co/kiyoung2/koelectra-small/resolve/main/config.json
853 Bytes
| { | |
| "_name_or_path": "monologg/koelectra-small-v3-discriminator", | |
| "architectures": [ | |
| "ElectraForQuestionAnswering" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "embedding_size": 128, | |
| "end_n_top": 5, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 256, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1024, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "electra", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "start_n_top": 5, | |
| "summary_activation": "gelu", | |
| "summary_last_dropout": 0.1, | |
| "summary_type": "first", | |
| "summary_use_proj": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.13.0.dev0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 35000 | |
| } | |