Ondrej Dusek's starred repositories
LLaMA-Factory
Unify Efficient Fine-Tuning of 100+ LLMs
LLaMA-Efficient-Tuning
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
resize-font.gvim
gVim plugin for changing font/window size using keyboard or mousewheel.
stat-diag-sys
GPT-2 based NN connected to external knowledge base with 2-stage decoding for the Statistical Dialogue Systems course
stable-diffusion-webui
Stable Diffusion web UI
text-generation-webui
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
jsalt-dialogue-lab
Neural Task-Oriented Dialogue Lab at https://jsalt2023.univ-lemans.fr/en/summer-school.html
python-aiml-chatbot
Simplest chatbot in python, comes with ALICE 1.9 minimally modified AIML starter set
nanoChatGPT
A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick
Prompt-Engineering-Guide
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
openai-cookbook
Examples and guides for using the OpenAI API
awesome-align
A neural word aligner based on multilingual BERT
question_generation
Neural question generation using transformers
EDU-AI-asistent-editor
Prostředí pro návrh a provoz kurzů či procvičování - projekt AI asistent pro učitele a žáky
glove-python
Toy Python implementation of http://www-nlp.stanford.edu/projects/glove/
story-generation-eval
Code for the paper "Do Massively Pretrained Language Models Make Better Storytellers?"
example_deep_q_learning
Minimal working example (multi-armed bandit) for deep Q-learning using Tensorflow
dl-for-emo-tts
:computer: :robot: A summary on our attempts at using Deep Learning approaches for Emotional Text to Speech :speaker:
NL-Augmenter
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations
d2t_iterative_editing
Code for the paper Data-to-Text Generation with Iterative Text Editing
GenerationEval
WebNLG+ Challenge 2020: Scripts to evaluate the RDF-to-text task with automatic metrics (BLEU, METEOR, chrF++, TER and BERT-Score)