Aspartame-e951

Aspartame-e951's Stars

• kaiokendev/cutoff-len-is-context-len

  Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit

  Language:Python633

• turboderp/exllama

  A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

  Language:Python2.8k220

• ggerganov/llama.cpp

  LLM inference in C/C++

  Language:C++67.9k9.7k