A curated list of resources related to linear attention mechanisms.

MastermindEval for evaluating reasoning capabilities in LLMs @ ICLR 2025 Workshop on Reasoning and Planning of LLMs.

This repository contains the Hugging Face Agents Course.

Label shift estimation for transfer difficulty with Familiarity.

Lsp Plugin for working with Python virtual environments

🤗 smolagents: a barebones library for agents that think in python code.

🐸 Debug faster than a frog catches a fly

Efficiently find the best-suited language model (LM) for your NLP task

LAVIS - A One-stop Library for Language-Vision Intelligence

🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.

A modular graph-based Retrieval-Augmented Generation (RAG) system

XFUND: A Multilingual Form Understanding Benchmark

Official repository of the xLSTM.

A very simple news crawler with a funny name

Evaluate language models using multiple choice items

[LREC-Coling 2024] PECC: Problem Extraction and Coding Challenges

Bayesian IRT models in Python

[EACL '24] The repository to create LitSet (Large-Scale Label Interpretation Learning Scaling Entity Types)

Split bib files for anthology bibliography for overleaf

A framework for few-shot evaluation of language models.

New and clean Neovim config

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

prompt2model - Generate Deployable Models from Natural Language Instructions

phgrad - Cause there are not enough unusable autograd libraries in python

A high-throughput and memory-efficient inference and serving engine for LLMs

Structured Text Generation

Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning (Zhou et al.; EMNLP 2023 Findings)

Code of EMNLP 2023 paper "Revisiting Sparse Retrieval for Few-shot Entity Linking".