awesome-LLM-resourses
🧑🚀 全世界最好的LLM资料总结（数据处理、模型训练、模型部署、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.
https://github.com/WangRongsheng/awesome-LLM-resourses
Last synced: 4 days ago
JSON representation
-
评估 Evaluation
- aisuite
- DeepSeek-v3
- DeepEval - to-use, open-source LLM evaluation framework, for evaluating and testing large-language model systems.
- Lighteval - in-one toolkit for evaluating LLMs across multiple backends.
- QwQ/eval
- 火山引擎
- 文心千帆
- DashScope
- Groq
- 硅基流动
- VLMEvalKit - source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 40+ benchmarks.
- Weave
- lm-evaluation-harness - shot evaluation of language models.
- opencompass - 4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
- llm-comparator - by-side, developed.
- EvalScope
- Evaluation guidebook
- Ollama Benchmark
- 硅基流动
- MixEval
- AGI-Eval
- DeerAPI
- Qwen-Chat
- Evalchemy - to-use toolkit for evaluating post-trained language models.
- MathArena
- YourBench
-
知识库 RAG
- LightRAG - Agent-Generator pipelines.
- MiniRAG - augmented generation framework that enables small models to achieve good RAG performance through heterogeneous graph indexing and lightweight topology-enhanced retrieval.
- FlashRAG
- Quivr - augmented generation.
- Verba
- TEN - Gen AI-Agent Framework, the world's first truly real-time multimodal AI agent framework.
- nano-GraphRAG - to-hack GraphRAG implementation.
- RAG Techniques - Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.
- ragas
- kotaemon - source clean & customizable RAG UI for chatting with your documents. Built with both end users and developers in mind.
- Fast-GraphRAG
- AutoRAG
- RAGapp
- Tiny-GraphRAG
- AnythingLLM - in-one AI app for any LLM with full RAG and AI Agent capabilites.
- MaxKB
- RAGFlow - source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
- Dify - source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
- FastGPT - based platform built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization.
- Langchain-Chatchat
- QAnything
- GraphRAG - based Retrieval-Augmented Generation (RAG) system.
- RAGLite - Augmented Generation (RAG) with PostgreSQL or SQLite.
- XRAG - Augmented Generation (RAG) systems.
- TurboRAG - Augmented Generation with Precomputed KV Caches for Chunked Text.
- LightRAG - Augmented Generation.
- DB-GPT GraphRAG - GPT GraphRAG integrates both triplet-based knowledge graphs and document structure graphs while leveraging community and document retrieval mechanisms to enhance RAG capabilities, achieving comparable performance while consuming only 50% of the tokens required by Microsoft's GraphRAG. Refer to the DB-GPT [Graph RAG User Manual](http://docs.dbgpt.cn/docs/cookbook/rag/graph_rag_app_develop/) for details.
- Chonkie - nonsense RAG chunking library that's lightweight, lightning-fast, and ready to CHONK your texts.
- RAG-GPT - GPT, leveraging LLM and RAG technology, learns from user-customized knowledge bases to provide contextually relevant answers for a wide range of queries, ensuring rapid and accurate information retrieval.
- CAG
- GraphRAG-Ollama-UI
- KAG - guided reasoning and retrieval framework based on OpenSPG engine and LLMs.
- Rankify - Ranking, and Retrieval-Augmented Generation.
-
论文 Paper
- TÜLU 3: Pushing Frontiers in Open Language Model Post-Training
- Yi-Lightning Technical Report
- An Introduction to Vision-Language Modeling
- Gemma 3 Technical Report
- Predictable Scale: Part I -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining
- Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
- Baichuan Alignment Technical Report
- Huggingface Daily Papers - ai/ML-Papers-Explained)
- Hermes-3-Technical-Report
- The Llama 3 Herd of Models
- Qwen Technical Report
- Qwen2 Technical Report
- Qwen2-vl Technical Report
- DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- Baichuan 2: Open Large-scale Language Models
- DataComp-LM: In search of the next generation of training sets for language models
- OLMo: Accelerating the Science of Language Models
- MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series
- Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Jamba-1.5: Hybrid Transformer-Mamba Models at Scale
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs
- Baichuan-Omni Technical Report
- Model Merging Paper
- 1.5-Pints Technical Report: Pretraining in Days, Not Months – Your Language Model Thrives on Quality Data
- SkyLadder: Better and Faster Pretraining via Context Window Scheduling
- Phi-4 Technical Report
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models
- 2 OLMo 2 Furious
- Qwen2.5-VL Technical Report
- Baichuan-M1: Pushing the Medical Capability of Large Language Models
- Jamba: A Hybrid Transformer-Mamba Language Model
- Textbooks Are All You Need
- Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models
- OLMoE: Open Mixture-of-Experts Language Models
- Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
- Qwen2.5 Technical Report
- YuLan-Mini: An Open Data-efficient Language Model
- Qwen2.5-Omni technical report
- Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs
- Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources
-
Tips
- LLM-Dojo 开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架
- 基于 transformers 的 generate() 方法实现多样化文本生成：参数含义和算法原理解读
- 轻松入门大语言模型（LLM）
- Zero-Qwen-VL
- MiniMind
- Knowledge distillation: Teaching LLM's with synthetic data
- Part 1: Methods for adapting large language models
- Part 2: To fine-tune or not to fine-tune
- Part 3: How to fine-tune: Focus on effective datasets
- Reader-LM: Small Language Models for Cleaning and Converting HTML to Markdown
- Distributed Training Guide
- Chat Templates
- LLMs for Text Classification: A Guide to Supervised Learning
- Unsupervised Text Classification: Categorize Natural Language With LLMs
- Text Classification With LLMs: A Roundup of the Best Methods
- Tiny LLM Universe
- Zero-Chatgpt
- 
Programming Languages
Categories
Sub Categories
Keywords
llm
82
ai
38
rag
31
gpt
29
llama
29
llms
24
openai
23
python
23
large-language-models
22
agent
21
chatgpt
20
llama3
17
pytorch
13
qwen
13
chatbot
13
machine-learning
12
mistral
12
deep-learning
11
gpt-4
11
llama2
11
fine-tuning
11
langchain
10
ollama
10
deepseek
10
llava
9
llmops
9
nlp
9
transformers
8
llm-training
8
gemma
8
generative-ai
8
framework
8
llm-serving
7
artificial-intelligence
7
agents
7
pdf
7
language-model
6
lora
6
javascript
6
retrieval-augmented-generation
6
huggingface
6
genai
6
llm-inference
6
finetuning
6
evaluation
6
rlhf
6
transformer
6
ai-agents
5
mcp
5
chatglm
5