A simple, performant and scalable Jax LLM!

🖼️ Extract and process text from images with an OCR AI agent, featuring tools for image preprocessing and unit conversions.

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Phi4, ...) (AAAI 2025).

BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

Structural Field Theory (SFT): complete corpus with papers and reproducible runners (leptons, quarkonia, CKM, gravity-as-gradients, α topology). MIT.

Production-grade LLMOps Framework

Sapienza Sailing Team web app

https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成

EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO

A research sandbox for LLM pretraining, fine-tuning (SFT, DPO, RLHF), and alignment techniques. Designed for developing LLM-based solutions in computational biology.

This repo is making it accessible to fine tune your own LLM with SFT and DPO

Experimental fork of Nanotron, a minimalistic large language model 4D-parallelism training

LLM experiments for the GPU poor ;). How much research can you do on a T4 GPU?

25-2 YAI project

Code repository dedicated to experimenting and research with tiny reasoning language model

Military Named Entity Recognition with LoRA Fine-tuning

Build LLM from scratch