{"adoption": {"forks": 384, "observed_at": "2026-08-28T04:07:46.137827+00:00", "stars": 3152}, "canonical_url": "https://ross.abutalabs.com/products/how-to-train-your-gpt", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Build a modern LLM from scratch. Every line commented. Explained like we are five.", "domain": ["large-language-models", "deep-learning", "machine-learning", "tutorials", "education"], "enriched": true, "function": ["llm-training", "machine-learning", "deep-learning", "nlp", "transformers"], "health_score": 76, "homepage": null, "language": "Jupyter Notebook", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["raiyanyahya/how-to-train-your-gpt"], "name": "raiyanyahya/how-to-train-your-gpt", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-15T17:23:52+00:00", "repo": "raiyanyahya/how-to-train-your-gpt", "stars": 3152, "tags": ["pytorch", "gpt", "llama", "from-scratch", "tutorial", "jupyter-notebook", "attention-mechanism", "tokenization", "educational", "natural-language-processing", "gpu"], "topics": ["attention-mechanism", "deep-learning", "educational", "from-scratch", "gpt", "language-model", "llama", "llm", "machine-learning", "natural-language-processing", "python", "pytorch", "tokenisation", "transformers", "tutorial"], "urls": [], "use_cases": ["learn how transformers and attention work from scratch", "build a GPT-style language model in PyTorch", "understand LLaMA architecture internals like RoPE and KV cache", "study a fully commented LLM training loop", "teach myself deep learning without prior ML experience", "run a from-scratch language model training in Colab"], "what_it_is": "A 12-chapter educational repository that teaches how to build, train, and run a modern LLaMA-style GPT language model from scratch in Python/PyTorch, with every line of code commented. It includes 28 standalone topic explainers covering attention, RoPE, RMSNorm, SwiGLU, KV cache, and more.", "when_to_avoid": ["you need a production-ready LLM framework or inference server", "you want to fine-tune existing models efficiently at scale", "you need battle-tested, optimized training code for real workloads"], "when_to_choose": ["you want to understand LLM internals line by line rather than call APIs", "you have basic Python skills but no ML background", "you prefer analogies and step-by-step explanations over dense papers", "you want runnable notebooks for hands-on learning"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/how-to-train-your-gpt", "repo": "raiyanyahya/how-to-train-your-gpt", "role": "main", "score": 55}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:25:41.537124+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8d53d722bbc78987b9fb9852fb321393ac9dd356150a233db90d69dc362ce4de", "fetched_at": "2026-08-28T04:07:46.137827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/raiyanyahya/how-to-train-your-gpt"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:25:41.537124+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8d53d722bbc78987b9fb9852fb321393ac9dd356150a233db90d69dc362ce4de", "fetched_at": "2026-08-28T04:07:46.137827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/raiyanyahya/how-to-train-your-gpt"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:25:41.537124+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8d53d722bbc78987b9fb9852fb321393ac9dd356150a233db90d69dc362ce4de", "fetched_at": "2026-08-28T04:07:46.137827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/raiyanyahya/how-to-train-your-gpt"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:25:41.537124+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8d53d722bbc78987b9fb9852fb321393ac9dd356150a233db90d69dc362ce4de", "fetched_at": "2026-08-28T04:07:46.137827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/raiyanyahya/how-to-train-your-gpt"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:25:41.537124+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8d53d722bbc78987b9fb9852fb321393ac9dd356150a233db90d69dc362ce4de", "fetched_at": "2026-08-28T04:07:46.137827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/raiyanyahya/how-to-train-your-gpt"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:25:41.537124+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8d53d722bbc78987b9fb9852fb321393ac9dd356150a233db90d69dc362ce4de", "fetched_at": "2026-08-28T04:07:46.137827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/raiyanyahya/how-to-train-your-gpt"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:46.137827+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:25:41.537124+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8d53d722bbc78987b9fb9852fb321393ac9dd356150a233db90d69dc362ce4de", "fetched_at": "2026-08-28T04:07:46.137827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/raiyanyahya/how-to-train-your-gpt"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:25:41.537124+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8d53d722bbc78987b9fb9852fb321393ac9dd356150a233db90d69dc362ce4de", "fetched_at": "2026-08-28T04:07:46.137827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/raiyanyahya/how-to-train-your-gpt"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:25:41.537124+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8d53d722bbc78987b9fb9852fb321393ac9dd356150a233db90d69dc362ce4de", "fetched_at": "2026-08-28T04:07:46.137827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/raiyanyahya/how-to-train-your-gpt"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:25:41.537124+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8d53d722bbc78987b9fb9852fb321393ac9dd356150a233db90d69dc362ce4de", "fetched_at": "2026-08-28T04:07:46.137827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/raiyanyahya/how-to-train-your-gpt"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 92, "longevity": 8, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 122, "days_push": 49, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 55, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}