Pinned Repositories
1d-tokenizer
This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation
2025
academic-pretraining
$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
acme
A library of reinforcement learning components and agents
best-of-lists
sandboxing best-of-lists template with my nature-inspo stars
fart
fart on your code
ShibaTown
I didn't choose the ｓｈｉｂｅｌｉｆｅ、the shibe life chose me #shiba-grindset
TensorFlow-wheels
Custom built TensorFlow wheels for my machines
weight-selection
Xu et al. - 2023 - Initializing Models with Larger Ones - 2311.18823
evdcush's Repositories
evdcush/ADAS
Automated Design of Agentic Systems
evdcush/ai-notes
notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references under the /Resources folder.
evdcush/aideml
AIDE: the state-of-the-art machine learning engineer agent, generating machine learning solution code from natural language descriptions.
evdcush/awesome-japanese-llm
日本語LLMまとめ - Overview of Japanese LLMs
evdcush/Awesome-LLM4AD
A curated list of awesome LLM for Autonomous Driving resources (continually updated)
evdcush/Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.
evdcush/Awesome-Unified-Multimodal-Models
📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.
evdcush/cambrian
evdcush/Chest
🐸
evdcush/concordia
A library for generative social simulation
evdcush/DriveDreamer
[ECCV 2024] DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving
evdcush/gemma
Open weights LLM from Google DeepMind.
evdcush/gpt-researcher
GPT based autonomous agent that does online comprehensive research on any given topic
evdcush/lingua
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
evdcush/llm-datasets
High-quality datasets, tools, and concepts for LLM fine-tuning.
evdcush/LWM
evdcush/maxtext
A simple, performant and scalable Jax LLM!
evdcush/meltingpot
A suite of test scenarios for multi-agent reinforcement learning.
evdcush/metadrive
MetaDrive: Composing Diverse Scenarios for Generalizable Reinforcement Learning
evdcush/model2vec
The Fastest State-of-the-Art Static Embeddings in the World
evdcush/nevergrad
A Python toolbox for performing gradient-free optimization
evdcush/Open-LLM-VTuber
Talk to any LLM with hands-free voice interaction, voice interruption, Live2D taking face, and long-term memory running locally across platforms
evdcush/OpenAGI
OpenAGI: When LLM Meets Domain Experts
evdcush/opro
code for "Large Language Models as Optimizers"
evdcush/Qwen2.5
Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.
evdcush/research-town
A platform for developers to simulate research community
evdcush/schedule_free
Schedule-Free Optimization in PyTorch
evdcush/seamless_communication
Foundational Models for State-of-the-Art Speech and Text Translation
evdcush/torchtune
A Native-PyTorch Library for LLM Fine-tuning
evdcush/wandbot
wandbot is a technical support bot for Weights & Biases' AI developer tools that can run in Discord, Slack, ChatGPT and Zendesk