Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).

moe glm lora embedding liger peft kimi multimodal reranker sft megatron llm qwen deepseek grpo qwen3 qwen3-vl qwen3-omni jev

• Updated Nov 12, 2026
• Python

AI Agent 开发指南 | Agent Harness | 上下文工程 | 高级 RAG | MCP | Agentic RL 强化学习 | LangGraph 实战 | 1.2 万+ 大模型面试题 | 算法岗 / 开发岗求职 | 转行大模型

tutorial interview harness job-hunting rag sft ai-agent llm crewai graphrag grpo claude-code agenticrag agentic-rl

• Updated Nov 5, 2026
• MDX

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

python cli machine-learning transformers pytorch lora fine-tuning peft sft dpo huggingface llm llmops local-llm qlora local-ai ollama gguf low-vram consumer-gpu

• Updated Nov 12, 2026
• Python

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

reinforcement-learning inference pytorch llama lora gemma vlm synthetic-data fine-tuning sft dpo llm llms qwen llm-evaluation llm-as-a-judge agentic-ai tool-calling grpo gpt-oss

• Updated Nov 11, 2026
• Python

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

agent tutorial reinforcement-learning pytorch rl reinforcement ppo sft dpo llm rlhf agentic agentic-ai grpo llm-alignment agentic-rl

• Updated Oct 23, 2026
• Jupyter Notebook

Covers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning | 涵盖预训练数据、分词器、Transformer、MoE、分布式训练、缩放定律、推理与对齐，6 项渐进代码作业，掌握 LLM 全栈知识

nlp transformer rl cs336 gpu-programming sft datawhale scaling-laws llm grpo

• Updated Nov 9, 2026
• Jupyter Notebook

A simple, performant, and scalable Jax LLM!

gpt mistral fine-tuning jax sft large-language-models llm llama2 mixtral deepseek llama3 gemma2 gemma3 llama4

• Updated Nov 12, 2026
• Python

chatglm 6b finetuning and alpaca finetuning

deep-learning pytorch freeze lora sft chatglm p-tuning-v2 adalora qlora ia3

• Updated Mar 9, 2025
• Python

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

qa knowledge-graph data-generation question-answering data-synthesis sft pretrain pretraining graphgen ai4science llm llm-training qwen xtuner llama-factory sft-data

• Updated Nov 8, 2026
• Python

The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.

training machine-learning reinforcement-learning deep-learning deep-reinforcement-learning distributed artificial-intelligence multi-agent hyperparameter-optimization agents preference hpo reasoning post-training sft rft llm agilerl open-weight

• Updated Nov 12, 2026
• Python

Train and serve LLMs at extreme speed and massive throughput.

deep-learning cuda llama nvidia-gpu fine-tuning sft llm llms generative-ai qwen

• Updated Nov 5, 2026
• C++

A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T-N1.7, FastWAM, Cosmos3, DreamZero, DeepSeek-V4, GLM-5.3, Kimi-K3 and more.

gpu torch lora wan vla vlm wam sft megatron pretraining kunlun xpu llm mid-training

• Updated Nov 12, 2026
• Python

An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions. (DeepSeek-V3/R1 满血版 671B 全参数微调的开源解决方案，包含从训练到推理的完整代码和脚本，以及实践中积累一些经验和结论。)

python moe sft llm deepseek-r1

• Updated Mar 13, 2025
• Python

Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"

agent natural-language-processing character roleplay language-model sft large-language-models llm

• Updated Oct 29, 2024
• Python

聚宝盆(Cornucopia): 中文金融系列开源可商用大模型，并提供一套高效轻量化的垂直领域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)

nlp finance qa transformers text-generation chinese llama sft large-language-models rlhf

• Updated Jun 30, 2023
• Python

tensorflow를 사용하여 텍스트 전처리부터, Topic Models, BERT, GPT, LLM과 같은 최신 모델의 다운스트림 태스크들을 정리한 Deep Learning NLP 저장소입니다.

nlp natural-language-processing tensorflow transformers named-entity-recognition question-answering llama lora trainer bert keras-tutorial sft dpo nlp-tutorial huggingface bert-ner llm

• Updated Jun 5, 2026
• Jupyter Notebook

Awesome-RAG: Collect typical RAG papers and systems.

agent awesome opensource ai paper awesome-list mm rag sft llm graphrag

• Updated Aug 4, 2025

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

agent machine-learning reinforcement-learning self-hosted rl post-training sft llm local-llm local-ai agentic-ai grpo

• Updated Nov 12, 2026
• Python

AI-powered vocabulary learning — a fine-tuned 1.5B model (SFT+DPO) that runs offline in your browser. Live: wordlink.lifeplayertribe.com

nextjs webgpu english-learning fine-tuning sft dpo ai-education sdg4 llm modelscope qwen

• Updated Nov 5, 2026
• TypeScript

Open-source code for training and scaling up energy-based foundation models.

reinforcement-learning ai rl language-models fine-tuning post-training sft pre-training energy-based-models scaling-laws foundation-models llm scaling-law pretraining-model large-language-model fineweb climbmix energy-based-language-models dclm energy-based-generation

• Updated Nov 3, 2026
• Python