dadelani

dadelani's Stars

• facebookresearch/seamless_communication

  Foundational Models for State-of-the-Art Speech and Text Translation

  Language:Jupyter Notebook10.5k1393331k

• xenova/transformers.js

  State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

  Language:JavaScript9.9k70510588

• huggingface/optimum

  🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

  Language:Python2.3k59695400

• THUDM/P-tuning-v2

  An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

  Language:Python1.9k2972194

• bazingagin/npc_gzip

  Code for Paper: “Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors

  Language:Python1.8k2521155

• epfLLM/meditron

  Meditron is a suite of open-source medical Large Language Models (LLMs).

  Language:Python1.8k2928157

• pbelcak/UltraFastBERT

  The repository for the code of the UltraFastBERT paper

  Language:Python494151333

• Unbabel/COMET

  A Neural Framework for MT Evaluation

  Language:Python4371715972

• facebookresearch/belebele

  Repo for the Belebele dataset, a massively multilingual reading comprehension dataset.

  Language:Python3056821

• achernodub/targer

  BiLSTM-CNN-CRF tagger

  Language:Python25013764

• LasseRegin/medical-question-answer-data

  Medical question and answer dataset gathered from the web.

  11610133

• ylacombe/finetune-hf-vits

  Finetune VITS and MMS using HuggingFace's tools

  Language:Python9282821

• google-research/mt-metrics-eval

  Tools for evaluating the performance of MT metrics on data from recent WMT metrics shared tasks.

  Language:Python7331112

• FreedomIntelligence/MultilingualSIFT

  MultilingualSIFT: Multilingual Supervised Instruction Fine-tuning

  Language:Python71734

• MarsPanther/Amharic-English-Machine-Translation-Corpus

  Amharic English Machine Translation Corpus prepared through website crawelling and custom preprocessing.

  Language:Python376023

• ehsanasgari/1000Langs

  Creating super-parallel corpora of more than 1500+ unique languages for NLP research

  Language:HTML31747

• asahi417/lm-vocab-trimmer

  Vocabulary Trimming (VT) is a model compression technique, which reduces a multilingual LM vocabulary to a target language by deleting irrelevant tokens from its vocabulary. This repository contains a python-library vocabtrimmer, that remove irrelevant tokens from a multilingual LM vocabulary for the target language.

  Language:Python26230

• konstantinjdobler/focus

  [EMNLP 2023] Official Code for "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models"

  Language:Python26111

• masakhane-io/masakhane-news

  MasakhaNEWS: News Topic Classification for African Languages

  Language:Python141016

• stefan-it/xlm-v-experiments

  Experiments for XLM-V Transformers Integeration

  Language:Python13223

• castorini/AfriTeVa-keji

  Language:Python10204

• mainlp/How-to-distill-your-BERT

  Code for the paper: How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives (ACL 2023)

  Language:Python8302

• wulinjuan/Struct-XLM

  The code of paper accepted in EMNLP2023, Struct-XLM: A Structure Discovery Multilingual Language Model for Enhancing Cross-lingual Transfer through Reinforcement Learning.

  Language:Python721

• cisnlp/Taxi1500

  Language:Python5520

• gpengzhi/CrossConST-SR

  Code for EMNLP 2023 industry track paper "Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization"

  Language:Python5220

• ZindiAfrica/Natural-Language-Processing-NLP

  Machine Translation, ASR, Sentiment Analysis, Classification solutions

  Language:Jupyter Notebook5102

• parovicm/unified-xlt

  Language:Python3100

• ashatilov/zindi_masakhane_pos

  Code for Lacuna Masakhane Parts of Speech Classification Challenge

  Language:Jupyter Notebook2104

• zsquaredz/joint_multilingual_analysis

  This repository contains code for the paper "A Joint Matrix Factorization Analysis of Multilingual Representations" which appears in EMNLP2023 Findings

  Language:Python2100

• mo-arvan/scholarly-metadata

  Language:Python1101