Pinned Repositories
alignment-handbook
Robust recipes to align language models with human and AI preferences
course
The Hugging Face course on Transformers
diffusion-models-class
Materials for the Hugging Face Diffusion Models Course
setfit
Efficient few-shot learning with Sentence Transformers
trl
Train transformer language models with reinforcement learning.
dl4phys
Deep learning for particle physicists
dslectures
Course materials for introductory data science
hepml
Practical machine learning for physicists
notebooks
Jupyter notebooks for the Natural Language Processing with Transformers book
lewtun's Repositories
lewtun/dslectures
Course materials for introductory data science
lewtun/hepml
Practical machine learning for physicists
lewtun/awesome-rlhf
A curated list of resources dedicated to Reinforcement Learning from Human Feedback (RLHF).
lewtun/chatty-lms
A Hugging Face Space to compare various dialogue-prompted language models
lewtun/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
lewtun/deepcode
Machine learning on source code for the Rocket platform
lewtun/pretraining-with-human-feedback
Code accompanying the paper Pretraining Language Models with Human Preferences
lewtun/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
lewtun/alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
lewtun/BIG-bench
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
lewtun/chatgpt-failures
Failure archive for ChatGPT and similar models
lewtun/course
The Hugging Face course
lewtun/distilabel
⚗️ AI Feedback framework for scalable LLM alignment
lewtun/easyllm
lewtun/FLAN
lewtun/following-instructions-human-feedback
lewtun/google-research
Google Research
lewtun/langchain
⚡ Building applications with LLMs through composability ⚡
lewtun/language-model-agents
Experiments with generating opensource language model assistants
lewtun/lm-evaluation-harness
A framework for few-shot evaluation of language models.
lewtun/MixEval
The official evaluation suite and dynamic data release for MixEval.
lewtun/Open-Assistant
lewtun/orpo
Official repository for ORPO
lewtun/rlhf-interface
lewtun/self-instruct
Aligning pretrained language models with instruction data generated by themselves.
lewtun/SPIN
The official implementation of Self-Play Fine-Tuning (SPIN)
lewtun/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
lewtun/SubjQA
A question-answering dataset with a focus on subjective information
lewtun/trl
Train transformer language models with reinforcement learning.
lewtun/WebShop
[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents