A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆28 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

nlp natural-language-processing text-classification glue pytorch transformer imagenet image-classification coco object-detection semantic-segmentation knowledge-distillation cifar10 pascal-voc cifar100 google-colab colab-notebook amazon-sagemaker-lab causal-language-modeling pytorch-ecosystem

• Updated Nov 12, 2026
• Python

Repository for My HuggingFace Natural Language Processing Projects

sentiment-analysis text-classification machine-translation language-detection question-answering text-summarization semantic-similarity binary-classification text-regression multiclass-classification multilabel-classification huggingface multiple-choice-question-answering text-classification-multi-label text-classificaiton-with-bert causal-language-modeling masked-language-modeling

• Updated Aug 31, 2023
• Jupyter Notebook

Auto-regressive causal language model for molecule (SMILES) and reaction template (SMARTS) generation based on the Hugging Face implementation of OpenAI's GPT-2 transformer decoder model

transformer reactions auto-regressive-model molecules gpt-2 huggingface causal-language-modeling

• Updated Jun 1, 2024
• Jupyter Notebook

Codebase for Linguistic Collapse: Neural Collapse in (Large) Language Models [NeurIPS 2024] [arXiv:2405.17767]

language-model gpt-neo large-language-models causal-language-modeling neural-collapse large-language-model tinystories

• Updated Apr 14, 2025
• Python

Transformers Intuition

transformers embeddings semantic-similarity sequence-to-sequence tokenization attention-is-all-you-need encoder-decoder-model encoder-model decoder-model masked-language-models causal-language-modeling

• Updated May 12, 2025
• Jupyter Notebook

Links to my repositories, where I implement a wide variety of Natural Language Processing models using TensorFlow and Hugging Face.

python natural-language-processing translation text-classification tensorflow scikit-learn plotly transformers lstm question-answering summarization gpt bert roberta t5 marianmt hugging-face token-classification causal-language-modeling

• Updated Oct 5, 2024

A multi-threaded GitHub scraper to collect Python code with docstrings from public repositories, creating a well-documented dataset for the JaraConverse LLM model.

nlp scraper script python3 dataset dataset-generation nlp-machine-learning data-scraping github-scraper python-code docstring-generator llm causal-language-modeling dataset-scripts python-dataset llm-training docst

• Updated Jul 21, 2024
• Python

Open source implementation of AMALIA: A Fully Open Large Language Model for European Portuguese

open-source machine-learning deep-learning decoder inference text-generation pytorch artificial-intelligence portugal gpt quantization rope pytorch-implementation large-language-models llm causal-language-modeling llms llm-inference decoder-only group-query-attention

• Updated Oct 10, 2026
• Python

Change the Bert model to a GPT-style autoregressive decoder.

decoder transformer bert causal-language-modeling

• Updated Jan 27, 2025
• Python

This repository is for the paper Lexical Substitution as Causal Language Modeling. In Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024), Mexico City, Mexico. Association for Computational Linguistics.

naacl language-modeling gpt lexical-substitution star-sem naacl-paper prompt-tuning causal-language-modeling naacl2024

• Updated Jul 1, 2024
• Python

CUDA-native residual-frame Delta memory for causal language models: full-matrix prefix geometry, rank-one recurrent updates, exact local similarity, Hugging Face integration, and CUDA Graph training.

cuda pytorch triton online-learning delta-rule sequence-modeling huggingface-transformers linear-attention causal-language-modeling long-context flash-linear-attention recurrent-memory

• Updated Sep 2, 2026
• Python

HelixLM - a recurrent heterogeneous graph neural LLM combining biological neural column random wiring, hybrid attention, and Mamba-2 for hyperpersonalized and on-device AI.

pytorch neuromorphic mamba state-space-model embedded-ai edge-ai on-device-ai heterogeneous-graph-neural-network huggingface-transformers efficient-transformers cpu-inference llm causal-language-modeling long-context local-llm small-language-models hybrid-attention openmythos helixlm recurrent-language-model

• Updated Sep 14, 2026
• Python

Causal language modeling and intent classification using GPT-2.

pytorch intent-classification gpt-2 huggingface causal-language-modeling

• Updated Mar 4, 2024
• Python

A quick and easy way to interact with open-source LLMs.

llm causal-language-modeling

• Updated Sep 9, 2024
• Python

reactjs transformer webapp fastapi large-language-models causal-language-modeling

• Updated Nov 14, 2023
• Jupyter Notebook

python tensorflow plotly gpt-2 distilgpt2 hugging-face causal-language-modeling

• Updated Jul 6, 2024
• Jupyter Notebook

Fine-tuning (or training from scratch) the library models for language modeling on a text dataset for GPT, GPT-2, ALBERT, BERT, DitilBERT, RoBERTa, XLNet... GPT and GPT-2 are trained or fine-tuned using a causal language modeling (CLM) loss while ALBERT, BERT, DistilBERT and RoBERTa are trained or fine-tuned using a masked language modeling (MLM…

text-classification transformers text-generation language-model huggingface causal-language-modeling

• Updated Apr 3, 2025
• Python

An AI generated picturebook.

pytorch dataset gpt-2 huggingface-transformers causal-language-modeling

• Updated Feb 25, 2023
• Python

Course materials for the Machine Learning for NLP course taught by Sameer Singh for the Cognitive Science summer school 2022.

nlp word-embeddings nlp-machine-learning zero-shot-learning few-shot-learning gpt-2 gpt-3 causal-language-modeling masked-language-modeling tk-instruct

• Updated Aug 7, 2022
• Jupyter Notebook

Rescoring Automatic Speech Recognition using Large Language Models

speech-recognition gpt bert asr rescore masked-language-models llm causal-language-modeling

• Updated Mar 13, 2024
• Jupyter Notebook