Efficient Few-Shot Learning with Sentence Transformers

preview_player
Показать описание
Join researchers from Hugging Face, Intel Labs, and UKP for a presentation about their recent work on SetFit, a new framework for few-shot learning with language models.

  1. HuggingFace
Рекомендации по теме
Efficient Few-Shot Learning 1:06:43

Efficient Few-Shot Learning with Sentence Transformers

SetFit - Efficient 0:12:42

SetFit - Efficient Few-shot Learning with Sentence Transformers |#SetFit | Pybron

SetFit - Efficient 0:09:43

SetFit - Efficient Few-Shot Learning Without Prompts (Research Paper Walkthrough)

Efficient Few-Shot Learning 0:06:42

Efficient Few-Shot Learning on CPU with SetFit

Few Shot Learning 0:10:01

Few Shot Learning - EXPLAINED!

Zero-shot, One-shot and 0:03:46

Zero-shot, One-shot and Few-shot Prompting Explained | Prompt Engineering 101

Few-shot learning with 0:00:32

Few-shot learning with SetFit

Few-Shot Learning (1/3): 0:18:39

Few-Shot Learning (1/3): Basic Concepts

Efficient Fine-tuning of 0:06:54

Efficient Fine-tuning of LLMs for SysML Model Generation

Few-shot learning methods 0:00:14

Few-shot learning methods

SetFit: Few Shot 0:11:36

SetFit: Few Shot Learning for Text Classification

SetFit (Sentence Transformer 0:09:56

SetFit (Sentence Transformer Fine-tuning) | Few shot Text Classification | Code & Theory Explana...

Efficient few-shot learning 0:03:53

Efficient few-shot learning for pixel-precise handwritten document layout analysis

Few-Shot Parameter-Efficient Fine-Tuning 0:12:44

Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

Multimodal Few-Shot Learning 0:21:01

Multimodal Few-Shot Learning with Frozen Language Models | Paper Explained

CODE SetFit w/ 0:28:17

CODE SetFit w/ SBERT for Text Classification (Few-Shot Learning) multi-class multi-label (SBERT 44)

Few-Shot Learning (3/3): 0:27:31

Few-Shot Learning (3/3): Pretraining + Fine-tuning

Few-Shot Text Classification 0:25:16

Few-Shot Text Classification in the Real-World

SETFIT Few-Shot Learning 0:18:33

SETFIT Few-Shot Learning outperforms GPT-3 | SBERT Text Classification (SBERT 43)

[AutoMLConf'22]:Meta-Adapters: Parameter Efficient 0:01:50

[AutoMLConf'22]:Meta-Adapters: Parameter Efficient Few-shot Fine-tuning through Meta-Learning T...

Few-shot Learning Explained 0:01:39

Few-shot Learning Explained (FSL): AI with Minimal Data

Few-Shot Text Classification 0:16:46

Few-Shot Text Classification Tutorial with SetFit | Few-Shot Learning in NLP

LLM Module 4: 0:03:05

LLM Module 4: Fine-tuning and Evaluating LLMs | 4.4 Fine Tuning: Few-shot Learning

Few-shot learning in 1:21:41

Few-shot learning in production

Комментарии
Автор

Very interesting and useful information! Thanks!

gigabytechanz
Автор

This is great. Would you have any performance comparisons between SetFit and deberta (say, v3) on NLI tasks? Also, how many examples are needed to fine tune these models. Thanks

sanjaychawla
Автор

Can SetFit be used for topic modeling (find the topics that a text deals with)?

andrea-mjce
Автор

Can this used for a Regression Task? e.g. comparing answers and calculate the score based on its similarity.

mikael_aldo
Автор

for num examples 640 how is it calculated?

jacehua
Автор

hi, If i want to train the model with my own dataset how do i prepare the dataset ? I am passing the train and eval data as dictionary but its not able to read the colnames. how do I prepare my own data to train this model ?

rajibahsan
Автор

pineapple and pizza are too distant in flavor space 😋

X
Автор

huggings face 'emoticon' is so annoying for the excellent presentation. It adds noise to the communication

CppExpedition