open clipAn open source implementation of CLIP.
cscgCode Generation as a Dual Task of Code Summarization.
CoLAKECOLING'2020: CoLAKE: Contextualized Language and Knowledge Embedding
gpt-j-apiAPI for the GPT-J language model 🦜. Including a FastAPI backend and a streamlit frontend
LM-CNLCChinese Natural Language Correction via Language Model
gdcCode for the ICLR 2021 paper "A Distributional Approach to Controlled Text Generation"
minGPT-TFA minimal TF2 re-implementation of the OpenAI GPT training
wechselCode for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.
PCPMPresenting Collection of Pretrained Models. Links to pretrained models in NLP and voice.
subword-lstm-lmLSTM Language Model with Subword Units Input Representations
backpropBackprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
dasher-webDasher text entry in HTML, CSS, JavaScript, and SVG
lm-scorer📃Language Model based sentences scoring library
gap-text2sqlGAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training
personality-predictionExperiments for automated personality detection using Language Models and psycholinguistic features on various famous personality datasets including the Essays dataset (Big-Five)
CharLMCharacter-aware Neural Language Model implemented by PyTorch
calmContext Aware Language Models
asr2424-hour Automatic Speech Recognition
KB-ALBERTKB국민은행에서 제공하는 경제/금융 도메인에 특화된 한국어 ALBERT 모델
Vaaku2VecLanguage Modeling and Text Classification in Malayalam Language using ULMFiT
rnn-theanoRNN(LSTM, GRU) in Theano with mini-batch training; character-level language models in Theano
pd3f🏭 PDF text extraction pipeline: self-hosted, local-first, Docker-based
COCO-LM[NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
TF-NNLM-TKA toolkit for neural language modeling using Tensorflow including basic models like RNNs and LSTMs as well as more advanced models.
PLBARTOfficial code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].