d1hr2uv

100Days

Agent-007

agents

🤗 Agents: the simplest building blocks to build and run LLM agents.

ai4chem_course

EPFL CH-457 "AI for chemistry"

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

Awesome-LLM4IE-Papers

Awesome papers about generative Information Extraction (IE) using Large Language Models (LLMs)

Awesome-Sign-Language

Paper list of sign language, including sign language recognition(SLR), sign language translation(SLT) and other interesting work. Quick start your awesome work with us!! 🤟🤟🤟

Awesome-SLP

A curated list of awesome work on Sign Language Production

google-summer-of-code

Rust project ideas for Google Summer of Code

KANO

Code and data for the Nature Machine Intelligence paper "Knowledge graph-enhanced molecular contrastive learning with functional prompt".

d1hr2uv/agents

🤗 Agents: the simplest building blocks to build and run LLM agents.

d1hr2uv/ARENA_3.0

d1hr2uv/attention-output-saes

Code to reproduce key results for "Interpreting Attention Layer Outputs with Sparse Autoencoders"

d1hr2uv/AutoencoderandVAE

d1hr2uv/cm4mlops

A collection of reusable and cross-platform automation recipes (CM scripts) with a human-friendly interface and minimal dependencies to make it easier to build, run, benchmark and optimize AI, ML and other applications and systems across diverse and continuously changing models, data sets, software and hardware (cloud/edge)

d1hr2uv/d1hr2uv

README.md

d1hr2uv/concordia

A library for generative social simulation

d1hr2uv/crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

d1hr2uv/d1hr2uv.github.io

d1hr2uv/Differential-Transformer-PyTorch

PyTorch implementation of the Differential-Transformer architecture for sequence modeling, specifically tailored as a decoder-only model similar to large language models (LLMs). The architecture incorporates a novel Differential Attention mechanism, Multi-Head structure, RMSNorm, and SwiGLU.

d1hr2uv/diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

d1hr2uv/dust3r

DUSt3R: Geometric 3D Vision Made Easy

d1hr2uv/easy-problems-that-llms-get-wrong

d1hr2uv/entropix

Entropy Based Sampling and Parallel CoT Decoding

d1hr2uv/equinox

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

d1hr2uv/Harkirat-Singh-course_code_and_notes

d1hr2uv/improving-RAG-systems-dhs2024

This repository will contain the presentation and python jupyter notebooks for the DataHack Summit 2024 conference talk, Improving Real-world Retrieval Augmented Generation Systems, focusing on the key challenges and practical solutions of how to solve them

d1hr2uv/inspect_ai

Inspect: A framework for large language model evaluations

d1hr2uv/LLM-Drop

The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".

d1hr2uv/ml-gsm-symbolic

GSM-Symbolic templates and generated data

d1hr2uv/mlops-2024

d1hr2uv/mlx-examples

Examples in the MLX framework

d1hr2uv/NewRepo

d1hr2uv/pose-to-video

Render pose sequences as photorealistic videos.

d1hr2uv/smol-course

A course on aligning smol models.

d1hr2uv/smoltropix

MLX port for xjdr's entropix sampler (mimics jax implementation)

d1hr2uv/Towards-Graph-Foundation-Models-New-perspective-

Accompanied repositories for our paper Graph foundation model

d1hr2uv/typst

A new markup-based typesetting system that is powerful and easy to learn.

d1hr2uv/VAE-Pytorch-ASL

This repository implements a simpleVAE for training on CPU on the MNIST dataset and provides ability to visualize the latent space, entire manifold as well as visualize how numbers interpolate between each other.

d1hr2uv/zml

High performance AI inference stack. Built for production. @ziglang / @openxla / MLIR / @bazelbuild