{"data":{"node":{"slug":"uclaml-spin","name":"SPIN","tagline":"Official implementation of Self-Play Fine-Tuning","github_url":"https://github.com/uclaml/SPIN","owner":"uclaml","repo":"SPIN","owner_avatar_url":"https://avatars.githubusercontent.com/u/22385378?v=4","primary_language":"Python","stars":1255,"forks":106,"topics":["deep-learning","fine-tuning","large-language-models","self-play"],"archived":false,"github_pushed_at":"2024-05-08T05:59:37+00:00","maintenance_label":"Dormant","stars_delta_30d":7,"url":"https://www.graphcanon.com/tools/uclaml-spin","markdown_url":"https://www.graphcanon.com/tools/uclaml-spin.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/uclaml-spin","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=uclaml-spin"},"categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"deep-learning","name":"deep-learning"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"large-language-models","name":"large-language-models"},{"slug":"self-play","name":"self-play"}],"edges":[],"neighbours":[{"slug":"huggingface-peft","name":"peft","tagline":"State-of-the-art Parameter-Efficient Fine-Tuning","github_url":"https://github.com/huggingface/peft","owner":"huggingface","repo":"peft","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":21704,"forks":2511,"topics":["adapter","diffusion","fine-tuning","llm","lora","parameter-efficient-learning","peft","python","pytorch","transformers"],"archived":false,"github_pushed_at":"2026-09-18T13:30:46+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-peft","markdown_url":"https://www.graphcanon.com/tools/huggingface-peft.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-peft","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-peft","shared_categories":["model-training","llm-frameworks"]},{"slug":"huggingface-trl","name":"trl","tagline":"Train transformer language models with reinforcement learning","github_url":"https://github.com/huggingface/trl","owner":"huggingface","repo":"trl","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":19336,"forks":3002,"topics":[],"archived":false,"github_pushed_at":"2026-09-18T06:20:19+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-trl","markdown_url":"https://www.graphcanon.com/tools/huggingface-trl.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-trl","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-trl","shared_categories":["model-training"]},{"slug":"opendilab-awesome-rlhf","name":"awesome-RLHF","tagline":"A curated list of reinforcement learning with human feedback resources (continually updated)","github_url":"https://github.com/opendilab/awesome-RLHF","owner":"opendilab","repo":"awesome-RLHF","owner_avatar_url":"https://avatars.githubusercontent.com/u/86840398?v=4","primary_language":null,"stars":4422,"forks":258,"topics":["deep-learning","deep-reinforcement-learning","human-feedback","large-language-models","reinforcement-learning","rlhf"],"archived":false,"github_pushed_at":"2026-05-20T12:56:15+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/opendilab-awesome-rlhf","markdown_url":"https://www.graphcanon.com/tools/opendilab-awesome-rlhf.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/opendilab-awesome-rlhf","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=opendilab-awesome-rlhf","shared_categories":["model-training"]},{"slug":"alibaba-roll","name":"ROLL","tagline":"Scaling Library for Reinforcement Learning with Large Language Models","github_url":"https://github.com/alibaba/ROLL","owner":"alibaba","repo":"ROLL","owner_avatar_url":"https://avatars.githubusercontent.com/u/1961952?v=4","primary_language":"Python","stars":3383,"forks":311,"topics":["agentic","rlhf","rlvr"],"archived":false,"github_pushed_at":"2026-09-06T01:30:14+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/alibaba-roll","markdown_url":"https://www.graphcanon.com/tools/alibaba-roll.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alibaba-roll","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alibaba-roll","shared_categories":["model-training"]},{"slug":"ashishpatel26-llm-finetuning","name":"LLM-Finetuning","tagline":"LLM Finetuning with PEFT","github_url":"https://github.com/ashishpatel26/LLM-Finetuning","owner":"ashishpatel26","repo":"LLM-Finetuning","owner_avatar_url":"https://avatars.githubusercontent.com/u/3095771?v=4","primary_language":"Jupyter Notebook","stars":2983,"forks":771,"topics":["falcon","fine-tuning","huggingface","llama","llama2","llm","llms","lora","peft","pytorch","text-generation"],"archived":false,"github_pushed_at":"2025-08-01T12:00:20+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/ashishpatel26-llm-finetuning","markdown_url":"https://www.graphcanon.com/tools/ashishpatel26-llm-finetuning.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ashishpatel26-llm-finetuning","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ashishpatel26-llm-finetuning","shared_categories":["model-training","llm-frameworks"]},{"slug":"keras-team-keras-tuner","name":"keras-tuner","tagline":"A Hyperparameter Tuning Library for Keras","github_url":"https://github.com/keras-team/keras-tuner","owner":"keras-team","repo":"keras-tuner","owner_avatar_url":"https://avatars.githubusercontent.com/u/34455048?v=4","primary_language":"Python","stars":2921,"forks":406,"topics":["automl","deep-learning","hyperparameter-optimization","keras","machine-learning","tensorflow"],"archived":false,"github_pushed_at":"2025-12-01T22:23:25+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/keras-team-keras-tuner","markdown_url":"https://www.graphcanon.com/tools/keras-team-keras-tuner.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/keras-team-keras-tuner","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=keras-team-keras-tuner","shared_categories":["model-training"]},{"slug":"learnables-learn2learn","name":"learn2learn","tagline":"A PyTorch Library for Meta-learning Research","github_url":"https://github.com/learnables/learn2learn","owner":"learnables","repo":"learn2learn","owner_avatar_url":"https://avatars.githubusercontent.com/u/54878124?v=4","primary_language":"Python","stars":2894,"forks":359,"topics":["few-shot","finetuning","learn2learn","learning2learn","maml","meta-descent","meta-learning","meta-optimization","meta-rl","metalearning","pytorch"],"archived":false,"github_pushed_at":"2025-12-16T20:53:41+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/learnables-learn2learn","markdown_url":"https://www.graphcanon.com/tools/learnables-learn2learn.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/learnables-learn2learn","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=learnables-learn2learn","shared_categories":["model-training"]},{"slug":"thudm-p-tuning-v2","name":"P-tuning-v2","tagline":"Optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks","github_url":"https://github.com/THUDM/P-tuning-v2","owner":"THUDM","repo":"P-tuning-v2","owner_avatar_url":"https://avatars.githubusercontent.com/u/48590610?v=4","primary_language":"Python","stars":2080,"forks":212,"topics":["natural-language-processing","p-tuning","parameter-efficient-learning","pretrained-language-model","prompt-tuning"],"archived":false,"github_pushed_at":"2023-11-16T04:38:09+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/thudm-p-tuning-v2","markdown_url":"https://www.graphcanon.com/tools/thudm-p-tuning-v2.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/thudm-p-tuning-v2","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=thudm-p-tuning-v2","shared_categories":["model-training"]},{"slug":"r6410418-jackrong-llm-finetuning-guide","name":"Jackrong-llm-finetuning-guide","tagline":"A guide for fine-tuning large language models like LLaMA3 and Qwen using PyTorch","github_url":"https://github.com/R6410418/Jackrong-llm-finetuning-guide","owner":"R6410418","repo":"Jackrong-llm-finetuning-guide","owner_avatar_url":"https://avatars.githubusercontent.com/u/115608084?v=4","primary_language":"Jupyter Notebook","stars":1693,"forks":270,"topics":["dataset","deepseek","fine-tuning","guide","llama3","llm","machine-learning","nlp","openai","pytorch","qwen","unsloth"],"archived":false,"github_pushed_at":"2026-07-11T05:10:47+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/r6410418-jackrong-llm-finetuning-guide","markdown_url":"https://www.graphcanon.com/tools/r6410418-jackrong-llm-finetuning-guide.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/r6410418-jackrong-llm-finetuning-guide","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=r6410418-jackrong-llm-finetuning-guide","shared_categories":["model-training","llm-frameworks"]},{"slug":"arahim3-mlx-tune","name":"mlx-tune","tagline":"Fine-tune LLMs on your Mac with Apple Silicon for various tasks including SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR.","github_url":"https://github.com/ARahim3/mlx-tune","owner":"ARahim3","repo":"mlx-tune","owner_avatar_url":"https://avatars.githubusercontent.com/u/41390319?v=4","primary_language":"Python","stars":1412,"forks":92,"topics":["apple-silicon","deep-learning","huggingface","large-language-models","llm","llm-finetuning","local-llm","lora","machine-learning","macos","mlx","on-device-ai","peft","speech-recognition","speech-to-text","text-to-speech","transformers","unsloth","vision-language-model","whisper"],"archived":false,"github_pushed_at":"2026-06-23T12:24:30+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/arahim3-mlx-tune","markdown_url":"https://www.graphcanon.com/tools/arahim3-mlx-tune.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/arahim3-mlx-tune","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=arahim3-mlx-tune","shared_categories":["model-training","llm-frameworks"]},{"slug":"georgian-io-llm-finetuning-toolkit","name":"LLM-Finetuning-Toolkit","tagline":"Toolkit for fine-tuning and testing open-source large language models","github_url":"https://github.com/georgian-io/LLM-Finetuning-Toolkit","owner":"georgian-io","repo":"LLM-Finetuning-Toolkit","owner_avatar_url":"https://avatars.githubusercontent.com/u/10764713?v=4","primary_language":"Python","stars":870,"forks":107,"topics":["ablation-study","classification","falcon","fine-tuning","finetuning","flan-t5","large-language-models","llama2","llm-test","lora","mistral-7b","nlp","nlp-machine-learning","qlora","redpajama","summarization","unit-testing","zephyr"],"archived":false,"github_pushed_at":"2026-05-04T16:33:40+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit","markdown_url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/georgian-io-llm-finetuning-toolkit","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=georgian-io-llm-finetuning-toolkit","shared_categories":["model-training","llm-frameworks"]},{"slug":"dvgodoy-finetuningllms","name":"FineTuningLLMs","tagline":"Official repository for 'A Hands-On Guide to Fine-Tuning LLMs with PyTorch and Hugging Face'","github_url":"https://github.com/dvgodoy/FineTuningLLMs","owner":"dvgodoy","repo":"FineTuningLLMs","owner_avatar_url":"https://avatars.githubusercontent.com/u/5184020?v=4","primary_language":"Jupyter Notebook","stars":865,"forks":119,"topics":["bitsandbytes","fine-tuning","finetuning","finetuning-llms","hugging-face","huggingface","large-language-models","llamacpp","lora","ollama","peft","peft-fine-tuning-llm","pytorch","transformers"],"archived":false,"github_pushed_at":"2026-02-28T14:57:29+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/dvgodoy-finetuningllms","markdown_url":"https://www.graphcanon.com/tools/dvgodoy-finetuningllms.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/dvgodoy-finetuningllms","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=dvgodoy-finetuningllms","shared_categories":["model-training","llm-frameworks"]}]}}