Instructions to use powerpuf-bot/wangchanberta-xet_ref-params with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use powerpuf-bot/wangchanberta-xet_ref-params 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="powerpuf-bot/wangchanberta-xet_ref-params")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("powerpuf-bot/wangchanberta-xet_ref-params") model = AutoModelForQuestionAnswering.from_pretrained("powerpuf-bot/wangchanberta-xet_ref-params", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from powerpuf-bot/wangchanberta-xet_ref-params: direct link, hf CLI and curl.
- Browser
- Download file 775 Bytes
-
https://huggingface.co/powerpuf-bot/wangchanberta-xet_ref-params/resolve/main/config.json
- Command line
-
hf download hf://powerpuf-bot/wangchanberta-xet_ref-params/config.json
-
curl -L -o config.json https://huggingface.co/powerpuf-bot/wangchanberta-xet_ref-params/resolve/main/config.json
775 Bytes
| { | |
| "_name_or_path": "Thammarak/wangchanBERTa-QA-thaiqa_squad", | |
| "architectures": [ | |
| "CamembertForQuestionAnswering" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "gradient_checkpointing": false, | |
| "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": "camembert", | |
| "num_attention_head": 12, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.2", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 25005 | |
| } | |