XiaoMi / subllm
This repository is the official implementation of the ECAI 2024 conference paper SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM
☆67Updated 8 months ago
Alternatives and similar repositories for subllm:
Users that are interested in subllm are comparing it to the libraries listed below
- An easy-to-use, fast, and easily integrable tool for evaluating audio LLM☆89Updated last week
- flow mirror models from JZX AI Labs☆45Updated 6 months ago
- ☆29Updated 5 years ago
- 语音识别 论文 前沿☆46Updated 3 years ago
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆56Updated last year
- 高性能文本 Tokenizer 库☆28Updated last year
- A ctc decoder for both online and offline asr model☆63Updated last year
- ☆74Updated 2 years ago
- 使用sentencepiece中BPE训练中文词表,并在transformers中进行使用。☆117Updated last year
- 基于FunASR实现语音识别,包含常规版和ONNX版(推荐)。☆39Updated 6 months ago
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆96Updated 2 years ago
- Qwen1.5-SFT(阿里, Ali), Qwen_Qwen1.5-2B-Chat/Qwen_Qwen1.5-7B-Chat微调(transformers)/LORA(peft)/推理☆57Updated 11 months ago
- FastThresholdClustering is an efficient vector clustering algorithm based on FAISS, particularly suitable for large-scale vector data clu…☆24Updated 4 months ago
- llama-omni训练代码复现☆60Updated 3 months ago
- ☆19Updated 11 months ago
- ☆38Updated 8 months ago
- 主要参考李宏毅老师2020年人类语言处理课程资料整理,包括代码和ppt☆35Updated 3 years ago
- Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction☆181Updated last month
- paraformer(chinense asr) online onnx runtime for python☆42Updated last year
- 用于汇总目前的开源中文对话数据集☆150Updated 2 years ago
- ☆84Updated last year
- This repository provides an implementation of the paper "A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Co…☆67Updated last month
- 多轮共情对话模型PICA☆92Updated last year
- [ICASSP2023] Source code, model links and open test sets for paper SeACo-Paraformer.☆28Updated last year
- 纯c++的全平台llm加速库,支持python调用,支持baichuan, glm, llama, moss基座,手机端流畅运行chatglm-6B级模型单卡可达10000+token / s,☆45Updated last year
- ☆71Updated 2 years ago
- 🤗 R1-AQA Model: mispeech/r1-aqa☆239Updated 3 weeks ago
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated last year
- A native-PyTorch library for large scale M-LLM (text/audio) training with tp/cp/dp/pp.☆52Updated this week
- 本项目旨在对大量文本文件进行快速编码检测和转换以辅助mnbvc语料集项目的数据清洗工作☆61Updated 6 months ago