SSamDav

learnDBN

Learning Dynamic Bayesian Network with missing values.

learnDBM

Learning Dynamic Bayesian Multinets.

aim

Aim — an easy-to-use and performant open-source experiment tracker.

CAA

Steering Llama 2 with Contrastive Activation Addition

ecco

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).

Layout-GNN

logseq-logarxivmate-plugin

marketplace

A centralized packages manager for Logseq marketplace plugins.

pymde

Minimum-distortion embedding with PyTorch

RWKV-Inference-Experiments

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

rwkv-long-range-arena

LRA Benchmark RWKV

safari

Convolutions for Sequence Modeling

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

trl

Train transformer language models with reinforcement learning.