zwshan

zwshan's Stars

• howard-hou/RWKV-TS

  RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks

  Language:Python783

• hithqd/PointRWKV

  Language:Python524

• Yaziwel/Restore-RWKV

  Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV

  Language:Python614

• 00ffcc/chunkRWKV6

  continous batching and parallel acceleration for RWKV6

  Language:Python23

• One-sixth/flash-linear-attention-pytorch

  A Python implementation of flash linear attention operators in TransnormerLLM.

  Language:Cuda111

• HqWu-HITCS/Awesome-Chinese-LLM

  整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

  16.1k1.5k

• ray-project/llmperf

  LLMPerf is a library for validating and benchmarking LLMs

  Language:Python648109

• ninehills/llm-inference-benchmark

  LLM Inference benchmark

  Language:Python35029

• yale-sys/prompt-cache

  Modular and structured prompt caching for low-latency LLM inference

  Language:Python697

• SpursGoZmy/Tabular-LLM

  本项目旨在收集开源的表格智能任务数据集（比如表格问答、表格-文本生成等），将原始数据整理为指令微调格式的数据并微调LLM，进而增强LLM对于表格数据的理解，最终构建出专门面向表格智能任务的大型语言模型。

  47938

• JL-er/RWKV-batch-infer

  Language:Python3

• BBuf/flash-rwkv

  Language:Python291

• macrozheng/mall-admin-web

  mall-admin-web是一个电商后台管理系统的前端项目，基于Vue+Element实现。 主要包括商品管理、订单管理、会员管理、促销管理、运营管理、内容管理、统计报表、财务管理、权限管理、设置等功能。

  Language:Vue11.9k7.2k

• lin-xin/vue-manage-system

  Vue3、Element Plus、typescript后台管理系统

  Language:Vue18.9k6k

• sustcsonglin/flash-linear-attention

  Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

  Language:Python1.3k70

• EleutherAI/lm-evaluation-harness

  A framework for few-shot evaluation of language models.

  Language:Python7k1.9k

• JL-er/RWKV-PEFT

  Language:Python8422

• ssbuild/rwkv_finetuning

  rwkv finetuning

  Language:Python361

• pappacena/pytorch-rocm-gtt

  Patch pytorch to allow ROCM APUs (like Ryzen processors' iGPU) to use more memory than the reserved

  Language:Makefile4

• datawhalechina/llms-from-scratch-cn

  仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

  Language:Jupyter Notebook1.6k228

• yuunnn-w/RWKV_Pytorch

  This is an inference framework for the RWKV large language model implemented purely in native PyTorch. The official native implementation is overly complex and lacks extensibility. Let's join the flexible PyTorch ecosystem and open-source it together!

  Language:Python1188

• AnshulRanjan2004/MicroRWKV

  Implementation of a custom architecture on nanoRWKV: A nanoGPT-style adaptation of the RWKV Language Model, which combines the simplicity of RNNs with GPT-level performance for large language models (LLMs).

  Language:Python21

• Hannibal046/nanoRWKV

  The nanoGPT-style implementation of RWKV Language Model - an RNN with GPT-level LLM performance.

  Language:Python19312

• deepglint/RWKV-CLIP

  [EMNLP 2024] RWKV-CLIP: A Robust Vision-Language Representation Learner

  Language:Python1118

• BlinkDL/RWKV-LM

  RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

  Language:Python12.7k866

• Hannibal046/RWKV-howto

  possibly useful materials for learning RWKV language model.

  252

• Sharpiless/Yolov5-Flask-VUE

  基于Flask+VUE前后端，在阿里云公网WEB端部署YOLOv5目标检测模型

  Language:Python18424

• charent/ChatLM-mini-Chinese

  中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。

  Language:Python1.3k151

• Hello-MLClub/ChatGLM-Finetuning

  本项目主要针对ChatGLM、ChatGLM2和ChatGLM3模型进行不同方式的微调（Freeze方法、Lora方法、P-Tuning方法、全量参数等），并对比大模型在不同微调方法上的效果，主要针对信息抽取任务、生成任务、分类任务等。

  Language:Python6

• AmberLJC/LLMSys-PaperList

  Large Language Model (LLM) Systems Paper List

  64924