{"data":{"node":{"slug":"trustedllm-regavae","name":"RegaVAE","tagline":"A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling","github_url":"https://github.com/TrustedLLM/RegaVAE","owner":"TrustedLLM","repo":"RegaVAE","owner_avatar_url":"https://avatars.githubusercontent.com/u/131944026?v=4","primary_language":"Python","stars":15,"forks":1,"topics":[],"archived":false,"github_pushed_at":"2023-12-05T20:52:31+00:00","maintenance_label":"Dormant","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/trustedllm-regavae","markdown_url":"https://www.graphcanon.com/tools/trustedllm-regavae.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/trustedllm-regavae","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=trustedllm-regavae"},"categories":[{"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":"gaussian-mixture-model","name":"gaussian mixture model"},{"slug":"hyperparameters","name":"hyperparameters"},{"slug":"language-modeling","name":"language modeling"},{"slug":"latent-space","name":"latent space"},{"slug":"retrieval-augmented","name":"retrieval-augmented"},{"slug":"training-data","name":"training data"},{"slug":"variational-auto-encoder","name":"variational auto-encoder"},{"slug":"yelp","name":"yelp"}],"edges":[],"neighbours":[{"slug":"tensorflow-tensorflow","name":"tensorflow","tagline":"An Open Source Machine Learning Framework for Everyone","github_url":"https://github.com/tensorflow/tensorflow","owner":"tensorflow","repo":"tensorflow","owner_avatar_url":"https://avatars.githubusercontent.com/u/15658638?v=4","primary_language":"C++","stars":200493,"forks":77664,"topics":["deep-learning","deep-neural-networks","distributed","machine-learning","ml","neural-network","python","tensorflow"],"archived":false,"github_pushed_at":"2026-09-27T05:55:11+00:00","maintenance_label":"Very active","stars_delta_30d":3735,"url":"https://www.graphcanon.com/tools/tensorflow-tensorflow","markdown_url":"https://www.graphcanon.com/tools/tensorflow-tensorflow.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tensorflow-tensorflow","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tensorflow-tensorflow","shared_categories":["model-training"]},{"slug":"huggingface-transformers","name":"transformers","tagline":"🤗 Transformers: state-of-the-art machine learning models for text, vision, audio, and multimodal models","github_url":"https://github.com/huggingface/transformers","owner":"huggingface","repo":"transformers","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":166279,"forks":34619,"topics":["audio","deep-learning","deepseek","gemma","glm","hacktoberfest","llm","machine-learning","model-hub","natural-language-processing","nlp","pretrained-models","python","pytorch","pytorch-transformers","qwen","speech-recognition","transformer","vlm"],"archived":false,"github_pushed_at":"2026-09-18T08:16:29+00:00","maintenance_label":"Very active","stars_delta_30d":2158,"url":"https://www.graphcanon.com/tools/huggingface-transformers","markdown_url":"https://www.graphcanon.com/tools/huggingface-transformers.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-transformers","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-transformers","shared_categories":["model-training"]},{"slug":"juliusbrussee-caveman","name":"caveman","tagline":"Reduces token usage by 65% through minimalistic language for coding agents","github_url":"https://github.com/JuliusBrussee/caveman","owner":"JuliusBrussee","repo":"caveman","owner_avatar_url":"https://avatars.githubusercontent.com/u/104168679?v=4","primary_language":"Go","stars":106401,"forks":6165,"topics":["ai","anthropic","caveman","claude","claude-code","llm","meme","prompt-engineering","skill","tokens"],"archived":false,"github_pushed_at":"2026-09-18T08:11:02+00:00","maintenance_label":"Very active","stars_delta_30d":7978,"url":"https://www.graphcanon.com/tools/juliusbrussee-caveman","markdown_url":"https://www.graphcanon.com/tools/juliusbrussee-caveman.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/juliusbrussee-caveman","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=juliusbrussee-caveman","shared_categories":["model-training"]},{"slug":"rasbt-llms-from-scratch","name":"LLMs-from-scratch","tagline":"Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","github_url":"https://github.com/rasbt/LLMs-from-scratch","owner":"rasbt","repo":"LLMs-from-scratch","owner_avatar_url":"https://avatars.githubusercontent.com/u/5618407?v=4","primary_language":"Jupyter Notebook","stars":105176,"forks":16121,"topics":["ai","artificial-intelligence","attention-mechanism","deep-learning","finetuning","from-scratch","generative-ai","gpt","instruction-tuning","language-model","large-language-models","llm","machine-learning","natural-language-processing","pretraining","python","pytorch","tokenizer","transformers"],"archived":false,"github_pushed_at":"2026-09-17T14:08:55+00:00","maintenance_label":"Very active","stars_delta_30d":2443,"url":"https://www.graphcanon.com/tools/rasbt-llms-from-scratch","markdown_url":"https://www.graphcanon.com/tools/rasbt-llms-from-scratch.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rasbt-llms-from-scratch","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rasbt-llms-from-scratch","shared_categories":["model-training"]},{"slug":"pytorch-pytorch","name":"pytorch","tagline":"Tensors and Dynamic neural networks in Python with strong GPU acceleration","github_url":"https://github.com/pytorch/pytorch","owner":"pytorch","repo":"pytorch","owner_avatar_url":"https://avatars.githubusercontent.com/u/21003710?v=4","primary_language":"Python","stars":103384,"forks":30659,"topics":["autograd","deep-learning","gpu","machine-learning","neural-network","numpy","python","tensor"],"archived":false,"github_pushed_at":"2026-09-27T05:57:49+00:00","maintenance_label":"Very active","stars_delta_30d":1240,"url":"https://www.graphcanon.com/tools/pytorch-pytorch","markdown_url":"https://www.graphcanon.com/tools/pytorch-pytorch.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pytorch-pytorch","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pytorch-pytorch","shared_categories":["model-training"]},{"slug":"deepseek-ai-deepseek-r1","name":"DeepSeek-R1","tagline":"Repository contains distilled LLM models derived from Qwen and LLaMA series for various commercial uses.","github_url":"https://github.com/deepseek-ai/DeepSeek-R1","owner":"deepseek-ai","repo":"DeepSeek-R1","owner_avatar_url":"https://avatars.githubusercontent.com/u/148330874?v=4","primary_language":null,"stars":91902,"forks":11656,"topics":[],"archived":false,"github_pushed_at":"2025-06-27T08:35:54+00:00","maintenance_label":"Dormant","stars_delta_30d":-118,"url":"https://www.graphcanon.com/tools/deepseek-ai-deepseek-r1","markdown_url":"https://www.graphcanon.com/tools/deepseek-ai-deepseek-r1.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/deepseek-ai-deepseek-r1","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=deepseek-ai-deepseek-r1","shared_categories":["model-training"]},{"slug":"mlabonne-llm-course","name":"llm-course","tagline":"Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.","github_url":"https://github.com/mlabonne/llm-course","owner":"mlabonne","repo":"llm-course","owner_avatar_url":"https://avatars.githubusercontent.com/u/81252890?v=4","primary_language":null,"stars":83011,"forks":9657,"topics":["course","large-language-models","llm","machine-learning","roadmap"],"archived":false,"github_pushed_at":"2026-02-05T13:09:26+00:00","maintenance_label":"Slowing","stars_delta_30d":1499,"url":"https://www.graphcanon.com/tools/mlabonne-llm-course","markdown_url":"https://www.graphcanon.com/tools/mlabonne-llm-course.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mlabonne-llm-course","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mlabonne-llm-course","shared_categories":["model-training"]},{"slug":"datawhalechina-hello-agents","name":"hello-agents","tagline":"A comprehensive guide to building intelligent agents from scratch","github_url":"https://github.com/datawhalechina/hello-agents","owner":"datawhalechina","repo":"hello-agents","owner_avatar_url":"https://avatars.githubusercontent.com/u/46047812?v=4","primary_language":"Python","stars":79727,"forks":9907,"topics":["agent","llm","rag","tutorial"],"archived":false,"github_pushed_at":"2026-09-17T12:00:56+00:00","maintenance_label":"Very active","stars_delta_30d":6601,"url":"https://www.graphcanon.com/tools/datawhalechina-hello-agents","markdown_url":"https://www.graphcanon.com/tools/datawhalechina-hello-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/datawhalechina-hello-agents","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=datawhalechina-hello-agents","shared_categories":["model-training"]},{"slug":"unslothai-unsloth","name":"unsloth","tagline":"Local UI for running and training LLMs and diffusion models","github_url":"https://github.com/unslothai/unsloth","owner":"unslothai","repo":"unsloth","owner_avatar_url":"https://avatars.githubusercontent.com/u/150920049?v=4","primary_language":"Python","stars":76344,"forks":6962,"topics":["agent","ai","chatgpt","deepseek","fine-tuning","gemma","image-generation","llama","llm","llms","openai","python","qwen","reinforcement-learning","self-hosted","stable-diffusion","text-to-speech","tts","ui","unsloth"],"archived":false,"github_pushed_at":"2026-09-18T08:00:38+00:00","maintenance_label":"Very active","stars_delta_30d":6723,"url":"https://www.graphcanon.com/tools/unslothai-unsloth","markdown_url":"https://www.graphcanon.com/tools/unslothai-unsloth.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/unslothai-unsloth","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=unslothai-unsloth","shared_categories":["model-training"]},{"slug":"hiyouga-llamafactory","name":"LlamaFactory","tagline":"Unified Efficient Fine-Tuning of 100+ LLMs & VLMs","github_url":"https://github.com/hiyouga/LlamaFactory","owner":"hiyouga","repo":"LlamaFactory","owner_avatar_url":"https://avatars.githubusercontent.com/u/16256802?v=4","primary_language":"Python","stars":74849,"forks":9170,"topics":["agent","ai","deepseek","fine-tuning","gemma","gpt","instruction-tuning","large-language-models","llama","llama3","llm","lora","moe","nlp","peft","qlora","quantization","qwen","rlhf","transformers"],"archived":false,"github_pushed_at":"2026-09-14T08:09:48+00:00","maintenance_label":"Very active","stars_delta_30d":717,"url":"https://www.graphcanon.com/tools/hiyouga-llamafactory","markdown_url":"https://www.graphcanon.com/tools/hiyouga-llamafactory.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hiyouga-llamafactory","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hiyouga-llamafactory","shared_categories":["model-training"]},{"slug":"compvis-stable-diffusion","name":"stable-diffusion","tagline":"A latent text-to-image diffusion model","github_url":"https://github.com/CompVis/stable-diffusion","owner":"CompVis","repo":"stable-diffusion","owner_avatar_url":"https://avatars.githubusercontent.com/u/30233788?v=4","primary_language":"Jupyter Notebook","stars":73442,"forks":10570,"topics":[],"archived":false,"github_pushed_at":"2024-06-18T01:53:49+00:00","maintenance_label":"Dormant","stars_delta_30d":188,"url":"https://www.graphcanon.com/tools/compvis-stable-diffusion","markdown_url":"https://www.graphcanon.com/tools/compvis-stable-diffusion.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/compvis-stable-diffusion","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=compvis-stable-diffusion","shared_categories":["model-training"]},{"slug":"headroomlabs-ai-headroom","name":"headroom","tagline":"Compress tool outputs, logs, files, and RAG chunks before they reach the LLM.","github_url":"https://github.com/headroomlabs-ai/headroom","owner":"headroomlabs-ai","repo":"headroom","owner_avatar_url":"https://avatars.githubusercontent.com/u/294291659?v=4","primary_language":"Python","stars":72850,"forks":5600,"topics":["agent","ai","anthropic","claude-code","compression","context-engineering","context-window","cursor","fastapi","langchain","llm","mcp","openai","prompt-engineering","proxy","python","rag","token-optimization","tokens","typescript"],"archived":false,"github_pushed_at":"2026-09-17T23:57:28+00:00","maintenance_label":"Very active","stars_delta_30d":6380,"url":"https://www.graphcanon.com/tools/headroomlabs-ai-headroom","markdown_url":"https://www.graphcanon.com/tools/headroomlabs-ai-headroom.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/headroomlabs-ai-headroom","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=headroomlabs-ai-headroom","shared_categories":["model-training"]}]}}