shifan3

Pinned Repositories

• AutoAWQ-llava-fix

  AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

  Language:Python0000

• ctc_decoder

  A ctc decoder for both online and offline asr model

  Language:C++00

• fast-autocomplete

  Fast Autocomplete: When Elastcsearch suggestions are not fast and flexible enough

  Language:Python0000

• go-ethereum

  Official Go implementation of the Ethereum protocol

  Language:Go0000

• llama.cpp

  Port of Facebook's LLaMA model in C/C++

  Language:C00

• LLaVA

  [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

  Language:Python00

• pt-search-deploy

  00

• QOL

  Language:C#0000

• sentence-transformers

  Sentence Embeddings with BERT & XLNet

  Language:Python0000

• symengine

  SymEngine is a fast symbolic manipulation library, written in C++

  Language:C++0000

shifan3's Repositories