inseq-team / inseq
Interpretability for sequence generation models π π
β361Updated 3 weeks ago
Related projects: β
- A python package for benchmarking interpretability techniques on Transformers.β207Updated 2 months ago
- Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"β424Updated last year
- Tools for understanding how transformer predictions are built layer-by-layerβ408Updated 3 months ago
- Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: β¦β321Updated last year
- This repository collects all relevant resources about interpretability in LLMsβ230Updated last week
- The official code of LM-Debugger, an interactive tool for inspection and intervention in transformer-based language models.β168Updated 2 years ago
- Repository for research in the field of Responsible NLP at Meta.β180Updated last month
- Organize your experiments into discrete steps that can be cached and reused throughout the lifetime of your research project.β525Updated 3 months ago
- Repository containing code for "How to Train BERT with an Academic Budget" paperβ309Updated last year
- Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventionsβ601Updated last week
- Package to compute Mauve, a similarity score between neural text and human text. Install with `pip install mauve-text`.β270Updated 2 months ago
- What's In My Big Data (WIMBD) - a toolkit for analyzing large text datasetsβ174Updated last week
- Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)β456Updated last year
- Seminar on Large Language Models (COMP790-101 at UNC Chapel Hill, Fall 2022)β309Updated last year
- Training Sparse Autoencoders on Language Modelsβ367Updated this week
- Contriever: Unsupervised Dense Information Retrieval with Contrastive Learningβ658Updated last year
- Scalable training for dense retrieval models.β268Updated last year
- Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Fβ¦β555Updated 10 months ago
- NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Dayβ248Updated 10 months ago
- β174Updated 4 months ago
- Datasets collection and preprocessings framework for NLP extreme multitask learningβ143Updated 2 months ago
- Aligning AI With Shared Human Values (ICLR 2021)β233Updated last year
- Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03β¦β508Updated 9 months ago
- Mechanistic Interpretability Visualizations using Reactβ175Updated 2 months ago
- List of papers on hallucination detection in LLMs.β561Updated last week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.β356Updated this week
- β65Updated last year
- PyTorch + HuggingFace code for RetoMaton: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including anβ¦β269Updated last year
- Erasing concepts from neural representations with provable guaranteesβ202Updated 3 months ago
- Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraintβ344Updated 5 months ago