txtai
💡 All-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows
rwkv-lm
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
prompt-engineering-guide
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
llms-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
https://github.com/blinkdl/chatrwkv
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
opennmt-py
Open Source Neural Machine Translation and (Large) Language Models in PyTorch
https://github.com/csinva/tree-prompt
Tree prompting: easy-to-use scikit-learn interface for improved prompting.
feste
Feste is a free and open-source framework allowing scalable composition of NLP tasks using a graph execution model that is optimized and executed by specialized schedulers.
https://github.com/csinva/interpretable-embeddings
Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)
https://github.com/google-research/jestimator
Amos optimizer with JEstimator lib.
https://github.com/cedrickchee/awesome-transformer-nlp
A curated list of NLP resources focused on Transformer networks, attention mechanism, GPT, BERT, ChatGPT, LLMs, and transfer learning.
https://github.com/chiang-yuan/llamp
A web app and Python API for multi-modal RAG framework to ground LLMs on high-fidelity materials informatics. An agentic materials scientist powered by @materialsproject, @langchain-ai, and @openai
spacy-wrap
spaCy-wrap is a wrapper library for spaCy for including fine-tuned transformers from Huggingface in your spaCy pipeline allowing you to include existing fine-tuned models within your SpaCy workflow.
https://github.com/brucewlee/h-test
[ACL 2024] Language Models Don't Learn the Physical Manifestation of Language
https://github.com/cvi-szu/linly
Chinese-LLaMA 1&2、Chinese-Falcon 基础模型;ChatFlow中文对话模型;中文OpenLLaMA模型;NLP预训练/指令微调数据集
https://github.com/amazon-science/mezo_svrg
Code the ICML 2024 paper: "Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models"
https://github.com/beomi/transformers-language-modeling
Train 🤗transformers with DeepSpeed: ZeRO-2, ZeRO-3
https://github.com/buaadreamer/dlpy
Programming Language for Deep Learning in Python
https://github.com/explosion/spacy-transformers
🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy
backprop
Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
https://github.com/beomi/gemma-easylm
Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)
https://github.com/cedrickchee/advent-of-code-2022
Advent of Code (AoC) 2022 in Rust
cramming
Cramming the training of a (BERT-type) language model into limited compute.
FMAT
😷 The Fill-Mask Association Test (FMAT): Measuring Propositions in Natural Language.
https://github.com/awslabs/gap-text2sql
GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training
https://github.com/awslabs/mlm-scoring
Python library & examples for Masked Language Model Scoring (ACL 2020)
https://github.com/alon-albalak/data-selection-survey
A Survey on Data Selection for Language Models
roberta-legal-portuguese
Related resources to the paper RoBERTaLexPT: A Legal RoBERTa Model pretrained with deduplication for Portuguese.
https://github.com/disi-unibo-nlp/easumm
[DATA22 and Springer LNCS] Graph-Enhanced Biomedical Abstractive Summarization via Factual Evidence Extraction
automated-brain-explanations
Generating and validating natural-language explanations for the brain.
speechbrain
A PyTorch-based Speech Toolkit
llms-from-scratch
Build your own Large Language Model from scratch with this code repository. Learn the ins and outs of LLMs like GPT. 🚀💻
https://github.com/amazon-science/bold
Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation" paper
https://github.com/csinva/iprompt
Finding semantically meaningful and accurate prompts.
snap-umls-clusters
Master Thesis Project in Arab American University Palestine with Palestinian Neuro Initiative Educational Research Center - Clustering medical sentences based on Unified Medical Language System (UMLS) terms and expanded UMLS terms present in them
movie-chatbot
A conversational agent that answers movie related questions based on a knowledge graph.
https://github.com/ac-rad/xdl-generation
CLAIRify: Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting
https://github.com/rentruewang/bocoel
Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few lines of modular code.
chronos
Debugging-first language model achieving 65.3% autonomous bug fixing (6-7x better than GPT-4). Research, benchmarks & evaluation framework. Model available Q1 2026 via Kodezi OS.
https://github.com/alexeyev/letnyayashkola-dl4nlp-2018
Deep Learning workshop @ letnyayashkola.org, supporting materials for lectures by @alexeyev [in Russian]
ai_story_scale
The AI story scale (AISS): A human rating scale for texts written with generative language models.
deeprank-gnn-esm
Graph Network for protein-protein interface including language model features