Hugging Face: dev
http://www.semanlink.net/tag/hugging_face_dev
Documents tagged with Hugging Face: devP-tuning for sequence classification
http://www.semanlink.net/doc/2023/08/p_tuning_for_sequence_classific
> It is challenging to finetune large language models for downstream tasks because they have so many parameters. To work around this, you can use prompts to steer the model toward a particular downstream task without fully finetuning a model. Typically, these prompts are handcrafted, which may be impractical because you need very large validation sets to find the best prompts. P-tuning is a method for automatically searching and optimizing for better prompts in a continuous space.
2023-08-28T12:21:20Zpeft/examples/token_classification/peft_lora_token_cls.ipynb at main · huggingface/peft
http://www.semanlink.net/doc/2023/08/peft_examples_token_classificat
2023-08-27T19:52:24ZLoRA for semantic similarity tasks
http://www.semanlink.net/doc/2023/07/lora_for_semantic_similarity_ta
> using a LoRA script to fine-tune a [intfloat/e5-large-v2](tag:e5) model on the smangrul/amazon_esci dataset (query, product_title, relevance_label) for semantic similarity tasks
2023-07-21T00:05:58ZSupport of very large dataset? - 🤗Datasets - Hugging Face Forums
http://www.semanlink.net/doc/2023/03/support_of_very_large_dataset_
[Big data? 🤗 Datasets to the rescue! - Hugging Face Course](doc:2023/03/big_data_🤗_datasets_to_the_re)
2023-03-12T12:14:56ZEfficient Training on a Single GPU
http://www.semanlink.net/doc/2023/02/efficient_training_on_a_single_
2023-02-16T11:35:46ZClass Labels for Custom Datasets - 🤗Datasets - Hugging Face Forums
http://www.semanlink.net/doc/2023/02/class_labels_for_custom_dataset
j'hallucine
2023-02-15T19:33:15Z