Search results

StreamingLLM gives language models unlimited context

bdtechtalks.com

StreamingLLM is a technique that can enable language models like Llama-2 to have conversations that span across millions of tokens.

These agents are initialized from the dataset, embodying varied social traits and preferences.

FunASR

github.com

Speech recognition toolkit with streaming ASR, VAD, punctuation, speaker diarization, and OpenAI-compatible serving for voice AI applications.

Image to text

huggingface.co

Showcase streaming text generation using the @huggingface/inference JS lib.

Summing Bird

github.com

Streaming MapReduce with Scalding and Storm.