rotary-positional-embedding
There are 5 repositories under rotary-positional-embedding topic.
Decoder-only-transformer_Time_Series_Prediction
使用Decoder-only的Transformer进行时序预测,包含SwiGLU和RoPE(Rotary Positional Embedding),Time series prediction using Decoder-only Transformer, Including SwiGLU and RoPE(Rotary Positional Embedding)
pytorch_video_classification
Transformer-Based Video Classification in PyTorch using RoPE
Language-Modelling
Implementations and Experiments: Transformers, RoPE, KV cache, SAEs, Tokenisers
llama3
A single-file implementation of LLaMA 3, with support for jitting, KV caching and prompting