https://finetune.kymatalabs.com The living index of LLM fine-tuning & post-training tooling — PEFT, LoRA, RLHF, trainers. https://finetune.kymatalabs.com/p/unslothai-unsloth/unslothai/unslothUnsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. https://finetune.kymatalabs.com/p/hiyouga-llamafactory/hiyouga/LlamaFactoryUnified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) https://finetune.kymatalabs.com/p/huggingface-peft/huggingface/peft🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. https://finetune.kymatalabs.com/p/modelscope-ms-swift/modelscope/ms-swiftUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025). https://finetune.kymatalabs.com/p/axolotl-ai-cloud-axolotl/axolotl-ai-cloud/axolotlGo ahead and axolotl questions https://finetune.kymatalabs.com/p/bentoml-openllm/bentoml/OpenLLMRun any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud. https://finetune.kymatalabs.com/p/ludwig-ai-ludwig/ludwig-ai/ludwigLow-code framework for building custom LLMs, neural networks, and other AI models https://finetune.kymatalabs.com/p/oumi-ai-oumi/oumi-ai/oumiEasily fine-tune, evaluate and deploy Gemma 4, Qwen3.5, Qwen3.6, gpt-oss, DeepSeek-R1, or any open source LLM / VLM! https://finetune.kymatalabs.com/p/flyteorg-flyte/flyteorg/flyteDynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI workflows. https://finetune.kymatalabs.com/p/thudm-slime/THUDM/slimeslime is an LLM post-training framework for RL Scaling. https://finetune.kymatalabs.com/p/kiln-ai-kiln/Kiln-AI/KilnBuild, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more. https://finetune.kymatalabs.com/p/shibing624-medicalgpt/shibing624/MedicalGPTMedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。 https://finetune.kymatalabs.com/p/h2oai-h2o-llmstudio/h2oai/h2o-llmstudioH2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/ https://finetune.kymatalabs.com/p/vllm-project-semantic-router/vllm-project/semantic-routerSystem Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge https://finetune.kymatalabs.com/p/daoyuanli2816-can-i-finetune-this/DaoyuanLi2816/can-i-finetune-thisEstimate whether a Hugging Face model fits and fine-tunes on your local GPU. https://finetune.kymatalabs.com/p/conardli-easy-dataset/ConardLi/easy-datasetA powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval https://finetune.kymatalabs.com/p/nerogar-onetrainer/Nerogar/OneTrainerOneTrainer is a one-stop solution for all your Diffusion training needs. https://finetune.kymatalabs.com/p/bghira-simpletuner/bghira/SimpleTunerA general fine-tuning kit geared toward image/video/audio diffusion models. https://finetune.kymatalabs.com/p/furkangozukara-stable-diffusion/FurkanGozukara/Stable-DiffusionFLUX, Stable Diffusion, SDXL, SD3, LoRA, Fine Tuning, DreamBooth, Training, Automatic1111, Forge WebUI, SwarmUI, DeepFake, TTS, Animation, Text To Video, Tutorials, Guides, Lectures, Courses, ComfyUI, Google Colab, RunPod, Kaggle, NoteBooks, ControlNet, TTS, Voice Cloning, AI, AI News, ML, ML News, https://finetune.kymatalabs.com/p/roboflow-maestro/roboflow/maestrostreamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL https://finetune.kymatalabs.com/p/google-tunix/google/tunixA Lightweight LLM Post-Training Library https://finetune.kymatalabs.com/p/pykeio-ort/pykeio/ortFast ML inference & training for ONNX models in Rust https://finetune.kymatalabs.com/p/ai-hypercomputer-maxtext/AI-Hypercomputer/maxtextA simple, performant and scalable Jax LLM! https://finetune.kymatalabs.com/p/dstackai-dstack/dstackai/dstackVendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal. https://finetune.kymatalabs.com/p/kubeflow-trainer/kubeflow/trainerDistributed AI Model Training and LLM Fine-Tuning on Kubernetes https://finetune.kymatalabs.com/p/radixark-miles/radixark/milesMiles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime. https://finetune.kymatalabs.com/p/vllm-project-vime/vllm-project/vimeAn LLM post-training framework with vLLM for RL Scaling https://finetune.kymatalabs.com/p/modelcloud-gptqmodel/ModelCloud/GPTQModelLLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang. https://finetune.kymatalabs.com/p/baidu-baige-loongforge/baidu-baige/LoongForgeA modular, scalable, high-performance training framework for LLMs, VLMs, diffusion, and embodied models. https://finetune.kymatalabs.com/p/mlabonne-llm-datasets/mlabonne/llm-datasetsCurated list of datasets and tools for post-training.