shuyhere
Follow
Lists (6)
Stars
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
The hub for EleutherAI's work on interpretability and learning dynamics
MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction
Mixed precision inference by Tensorrt-LLM
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
Tools for understanding how transformer predictions are built layer-by-layer
SGLang is a fast serving framework for large language models and vision language models.
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
Video Question Answering via Gradually Refined Attention over Appearance and Motion
Large language models to generate stable crystals.
🔥 Omni large models and datasets for understanding and generating multi-modalities.
Open source replication of Anthropic's Crosscoders for Model Diffing
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
Everything about the SmolLM & SmolLM2 family of models
Toolkit for attaching, training, saving and loading of new heads for transformer models
Training SAEs for your LLM, and visualize it in one place
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
A modern, high customizable, responsive Jekyll theme for documentation with built-in search.
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..
Collection of Reverse Engineering in Large Model