Lists (1)
Stars
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection
Evaluate your LLM's response with Prometheus and GPT4 💯
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
Easily embed, cluster and semantically label text datasets
A curated reading list of research in Mixture-of-Experts(MoE).
Repository accompanying "An Open Dataset and Model for Language Identification" (Burchell et al., 2023)
A collection of libraries to optimise AI model performances
TensorFlow - A curated list of dedicated resources http://tensorflow.org
Beautiful visualizations of how language differs among document types.
For those who want to model the inter-sentence relations, pls use the more powerful code of "Attentive Convolution" in another repository
Lime: Explaining the predictions of any machine learning classifier
Notebooks and code for the book "Introduction to Machine Learning with Python"
Semi-supervised learning frameworks for python, which allow fitting scikit-learn classifiers to partially labeled data
Open-Source Neural Machine Translation in Tensorflow
GloVe Word Embedding model's implementation in theano
Models and examples built with TensorFlow
Additional kernels that can be used with scikit-learn's Gaussian Process module
Python code for training all models in the ICLR paper, "Towards Universal Paraphrastic Sentence Embeddings". These models achieve strong performance on semantic similarity tasks without any trainin…
Common interface for Theano, CGT, and TensorFlow
Keras + Hyperopt: A very simple wrapper for convenient hyperparameter optimization
Matlab source code for the SONIG algorithm: Sparse Online Noisy-Input Gaussian process regression.
Simplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
Pretty Tensor: Fluent Networks in TensorFlow
Web interface for browsing, search and filtering recent arxiv submissions