Stars
Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, Iโฆ
A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.
Open source alternative to Gemini Deep Research. Generate reports with AI based on search results.
Building DeepSeek R1 from Scratch
Official Repo for Open-Reasoner-Zero
This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data
A reading list on LLM based Synthetic Data Generation ๐ฅ
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 ๐ and reasoning techniques.
AutoRAG ํ๊ตญ์ด ํํ ๋ฆฌ์ผ์ ์ํ ๋ ํฌ์ ๋๋ค.
Fully open reproduction of DeepSeek-R1
Medical Graph RAG: Graph RAG for the Medical Data
Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. Cโฆ
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
RAG that intelligently adapts to your use case, data, and queries
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
lectura7942 / KoAlpaca-finetune
Forked from Beomi/KoAlpacaKoAlpaca: ํ๊ตญ์ด ๋ช ๋ น์ด๋ฅผ ์ดํดํ๋ ์คํ์์ค ์ธ์ด๋ชจ๋ธ
HF Trainer + DeepSpeed๋ก ๋ค์ค GPU ํ๊ฒฝ์์ LLaMA2-7B ์ฌ์ ํ์ต
Code to reproduce experiments from the paper "Continual Pre-Training Mitigates Forgetting in Language and Vision" https://arxiv.org/abs/2205.09357
Code implementation of synthetic continued pretraining
Example project demonstrating how to implement GraphRAG
An example project demonstrating one approach to GraphRAG
ํ๊ตญ์ด ์๋ฃ ๋ถ์ผ ํนํ ์ฑ๋ด ํ๋ก์ ํธ
Recipes for shrinking, optimizing, customizing cutting edge vision models. ๐
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge baโฆ
A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.