{"adoption": {"forks": 869, "observed_at": "2026-08-28T04:09:28.132095+00:00", "stars": 5707}, "canonical_url": "https://ross.abutalabs.com/products/modded-nanogpt", "card": {"archived": false, "artifact_type": "learning-resource", "description": "NanoGPT (124M) in 90 seconds", "domain": ["deep-learning", "large-language-models", "gpu-computing", "tutorials"], "enriched": true, "function": ["llm-training", "benchmarking", "machine-learning"], "health_score": 78, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["KellerJordan/modded-nanogpt"], "name": "KellerJordan/modded-nanogpt", "platform": ["python"], "pushed_at": "2026-08-09T22:42:15+00:00", "repo": "KellerJordan/modded-nanogpt", "stars": 5707, "tags": ["nanogpt", "speedrun", "muon-optimizer", "h100", "training-efficiency", "pytorch", "fineweb", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["learn how to train a GPT-2 scale language model efficiently", "study modern LLM training optimizations like Muon and FP8", "benchmark GPU training speed for small language models", "find the fastest algorithm to train a 124M parameter transformer", "reproduce a fast GPT-2 replication on H100 GPUs", "learn modern transformer architecture tricks like QK-Norm and rotary embeddings"], "what_it_is": "A collaborative speedrun project that trains a GPT-2 (124M) scale language model to 3.28 validation loss on FineWeb in under 75 seconds on 8xH100 GPUs. It serves as both a record-setting training implementation and a learning resource showcasing modern LLM training techniques like the Muon optimizer, FP8, and architectural modernizations.", "when_to_avoid": ["you need a production training framework with configuration, checkpointing, and multi-dataset support", "you lack high-end NVIDIA GPUs, since the code is heavily tuned for 8xH100 setups", "you want to train large models or fine-tune existing ones rather than a fixed 124M GPT-2 scale target"], "when_to_choose": ["you want to learn state-of-the-art techniques for training small language models quickly", "you have access to 8xH100 GPUs and want to reproduce or compete in the speedrun", "you want a reference implementation of the Muon optimizer and modern GPT training tricks"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/modded-nanogpt", "repo": "KellerJordan/modded-nanogpt", "role": "main", "score": 67}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:53:32.730015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06472d0cc7612075a47b8055c1b0ab418d3302f65b96ae3deadd90db13a057d4", "fetched_at": "2026-08-28T04:09:28.132095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/KellerJordan/modded-nanogpt"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:53:32.730015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06472d0cc7612075a47b8055c1b0ab418d3302f65b96ae3deadd90db13a057d4", "fetched_at": "2026-08-28T04:09:28.132095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/KellerJordan/modded-nanogpt"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:53:32.730015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06472d0cc7612075a47b8055c1b0ab418d3302f65b96ae3deadd90db13a057d4", "fetched_at": "2026-08-28T04:09:28.132095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/KellerJordan/modded-nanogpt"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:53:32.730015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06472d0cc7612075a47b8055c1b0ab418d3302f65b96ae3deadd90db13a057d4", "fetched_at": "2026-08-28T04:09:28.132095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/KellerJordan/modded-nanogpt"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:53:32.730015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06472d0cc7612075a47b8055c1b0ab418d3302f65b96ae3deadd90db13a057d4", "fetched_at": "2026-08-28T04:09:28.132095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/KellerJordan/modded-nanogpt"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:53:32.730015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06472d0cc7612075a47b8055c1b0ab418d3302f65b96ae3deadd90db13a057d4", "fetched_at": "2026-08-28T04:09:28.132095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/KellerJordan/modded-nanogpt"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.132095+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:53:32.730015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06472d0cc7612075a47b8055c1b0ab418d3302f65b96ae3deadd90db13a057d4", "fetched_at": "2026-08-28T04:09:28.132095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/KellerJordan/modded-nanogpt"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:53:32.730015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06472d0cc7612075a47b8055c1b0ab418d3302f65b96ae3deadd90db13a057d4", "fetched_at": "2026-08-28T04:09:28.132095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/KellerJordan/modded-nanogpt"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:53:32.730015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06472d0cc7612075a47b8055c1b0ab418d3302f65b96ae3deadd90db13a057d4", "fetched_at": "2026-08-28T04:09:28.132095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/KellerJordan/modded-nanogpt"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:53:32.730015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06472d0cc7612075a47b8055c1b0ab418d3302f65b96ae3deadd90db13a057d4", "fetched_at": "2026-08-28T04:09:28.132095+00:00", "kind": "readme", "missing": false, "url": "https://github.com/KellerJordan/modded-nanogpt"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 58, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 823, "days_push": 24, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 67, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}