520zw

Pinned Repositories

• Selective_Context

  Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.

  Language:Python35042817

• LLMLingua

  [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

  Language:Python4.8k35135267

• PromptCompressor

  Language:Python10112

520zw's Repositories