r-three / common-pile

Related projects: ⓘ

• konstantinjdobler / focus
  [EMNLP'23] Official Code for "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models"
  ☆27Updated last week
• huggingface / olm-training
  Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.
  ☆91Updated last year
• MeLeLBGU / SaGe
  Code for SaGe subword tokenizer (EACL 2023)
  ☆21Updated this week
• bigscience-workshop / data_tooling
  Tools for managing datasets for governance and training.
  ☆77Updated last month
• malteos / clp-transfer
  Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning
  ☆29Updated last year
• allenai / bff
  ☆38Updated 5 months ago
• CPJKU / wechsel
  Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.
  ☆73Updated last week
• ZurichNLP / mbr
  Minimum Bayes Risk Decoding for Hugging Face Transformers
  ☆51Updated 3 months ago
• zouharvi / tokenization-scorer
  Simple-to-use scoring function for arbitrarily tokenized texts.
  ☆27Updated last week
• ltgoslo / ltg-bert
  LTG-Bert
  ☆25Updated 8 months ago
• google-research / t5x_retrieval
  ☆94Updated last year
• huggingface / that_is_good_data
  ☆65Updated last year
• castorini / hf-spacerini
  Plug-and-play Search Interfaces with Pyserini and Hugging Face
  ☆32Updated last year
• kpu / fasterText
  Library for fast text representation and classification.
  ☆28Updated 8 months ago
• EleutherAI / semantic-memorization
  ☆44Updated 2 months ago
• shayne-longpre / a-pretrainers-guide
  ☆73Updated last year
• google-research-datasets / swim-ir
  SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…
  ☆42Updated 10 months ago
• EleutherAI / lm-eval2
  ☆13Updated this week
• sebastian-hofstaetter / colberter
  ☆45Updated 2 years ago
• lovodkin93 / attribute-first-then-generate
  Repository for "Attribute First, then Generate: Locally-attributable Grounded Text Generation", ACL 2024
  ☆25Updated 5 months ago
• jxmorris12 / bm25_pt
  minimal pytorch implementation of bm25 (with sparse tensors)
  ☆82Updated 6 months ago
• flairNLP / transformer-ranker
  Efficiently find the best-suited language model (LM) for your NLP task
  ☆12Updated this week
• gonglinyuan / metro_t0
  Code repo for "Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers" (ACL 2023)
  ☆22Updated 10 months ago
• bigscience-workshop / metadata
  Experiments on including metadata such as URLs, timestamps, website descriptions and HTML tags during pretraining.
  ☆30Updated last year
• pchizhov / picky_bpe
  BPE modification that implements removing of the intermediate tokens during tokenizer training.
  ☆13Updated last week
• nreimers / flax-sentence-embeddings
  Shared code for training sentence embeddings with Flax / JAX
  ☆27Updated 3 years ago
• bigscience-workshop / multilingual-modeling
  BLOOM+1: Adapting BLOOM model to support a new unseen language
  ☆69Updated 6 months ago
• bminixhofer / zett
  Code for Zero-Shot Tokenizer Transfer
  ☆109Updated 2 months ago
• lemurproject / ClueWeb22
  ☆12Updated last year
• machelreid / m2d2
  M2D2: A Massively Multi-domain Language Modeling Dataset (EMNLP 2022) by Machel Reid, Victor Zhong, Suchin Gururangan, Luke Zettlemoyer
  ☆53Updated last year