spurscoder's Stars
comfyanonymous/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
helix-editor/helix
A post-modern modal text editor.
infiniflow/ragflow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
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。
liguodongiot/llm-action
本项目旨在分享大模型相关技术原理以及实战经验(大模型工程化、大模型应用落地)
QwenLM/Qwen2.5
Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.
mawww/kakoune
mawww's experiment for a better code editor
modelscope/FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
OpenBMB/MiniCPM
MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.
InternLM/InternLM
Official release of InternLM2.5 base and chat models. 1M context support
modelscope/agentscope
Start building LLM-empowered multi-agent applications in an easier way.
wdndev/llm_interview_note
主要记录大语言大模型(LLMs) 算法(应用)工程师相关的知识及面试题
open-compass/opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
jeinlee1991/chinese-llm-benchmark
中文大模型能力评测榜单:目前已囊括134个大模型,覆盖chatgpt、gpt-4o、谷歌gemini、百度文心一言、阿里通义千问、百川、讯飞星火、商汤senseChat、minimax等商用模型, 以及deepseek-v2.5、qwen2.5、llama3.1、glm4、书生internLM2.5、openbuddy、AquilaChat等开源大模型。不仅提供能力评分排行榜,也提供所有模型的原始输出结果!
DefTruth/Awesome-LLM-Inference
📖A curated list of Awesome LLM/VLM Inference Papers with codes, such as FlashAttention, PagedAttention, Parallelism, etc. 🎉🎉
underlines/awesome-ml
Curated list of useful LLM / Analytics / Datascience resources
OpenLMLab/MOSS-RLHF
Secrets of RLHF in Large Language Models Part I: PPO
AIoT-MLSys-Lab/Efficient-LLMs-Survey
[TMLR 2024] Efficient Large Language Models: A Survey
RUCAIBox/LLMBox
A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.
wdndev/llama3-from-scratch-zh
从零实现一个 llama3 中文版
RUC-GSAI/YuLan-Chat
YuLan: An Open-Source Large Language Model
allenai/OLMoE
OLMoE: Open Mixture-of-Experts Language Models
zhanshijinwat/Steel-LLM
Train a 1B LLM with 1T tokens from scratch by personal
naginoa/LLMs_interview_notes
LLMs interview notes and answers:该仓库主要记录大模型(LLMs)算法工程师相关的面试题和参考答案
vwxyzjn/lm-human-preference-details
RLHF implementation details of OAI's 2019 codebase
wdndev/tiny-rag
一个很小很小的RAG系统
hengjiUSTC/learn-llm
bansky-cl/tods-arxiv-daily-paper
task-oriented dialogue system, especially for LLM, contain subtask: (1) intent-detection (2) slot filling (3) dialogue state tracking
zhoucz97/awesome-ChatGPT
ChatGPT相关资源汇总
CrazyBoyM/LLM-Chinese
(撰写ing..)本仓库偏教程性质,以「模型中文化」为一个典型的模型训练问题切入场景,指导读者上手学习LLM二次微调训练。