-
EmerGen AI
- Minnesota, USA
-
11:54
(UTC -05:00)
Stars
A knowledge graph plotting using NELL (Never-Ending Language Learning)
Fast and Easy Infinite Neural Networks in Python
Deterministic algorithms for objective Bayesian inference and hyperparameter optimization
A simple implimentation of Bayesian Flow Networks (BFN)
Scripts for generating synthetic finetuning data for reducing sycophancy.
tairov / llama2.py
Forked from karpathy/llama2.cInference Llama 2 in one file of pure Python
A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.
This is the repo for the paper Shepherd -- A Critic for Language Model Generation
Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch
🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation
[ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers.
Official implementation of TransNormerLLM: A Faster and Better LLM
The implementation of "TabR: Unlocking the Power of Retrieval-Augmented Tabular Deep Learning"
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
This is a pytorch implementation of PCRNet
Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.
Swarm training framework using Haiku + JAX + Ray for layer parallel transformer language models on unreliable, heterogeneous nodes
Minimal Implementation of Bayesian Optimization in JAX
Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch
Implementation of Flash Attention in Jax
Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript
JAX - A curated list of resources https://github.com/google/jax
Unofficial implementation of forward-forward algorithm using jax
Images to inference with no labeling (use foundation models to train supervised models).
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.