{"adoption": {"forks": 126, "observed_at": "2026-08-28T04:04:49.793759+00:00", "stars": 1475}, "canonical_url": "https://ross.abutalabs.com/products/smolgpt", "card": {"archived": false, "artifact_type": "library", "description": null, "domain": ["large-language-models", "deep-learning", "machine-learning", "education", "tutorials"], "enriched": true, "function": ["llm-training", "llm-inference", "machine-learning", "deep-learning"], "health_score": 24, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["Om-Alve/smolGPT"], "name": "Om-Alve/smolGPT", "platform": ["python", "cross-platform"], "pushed_at": "2025-02-15T04:12:05+00:00", "repo": "Om-Alve/smolGPT", "stars": 1475, "tags": ["pytorch", "gpt", "transformer", "flash-attention", "tinystories", "educational", "from-scratch", "sentencepiece", "rope", "text-generation", "tokenization", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["train a small GPT model from scratch", "learn how transformers and LLMs work internally", "generate text with a custom-trained language model", "train an LLM on the TinyStories dataset", "experiment with flash attention and RoPE in PyTorch", "build a custom tokenizer with SentencePiece"], "what_it_is": "A minimal pure-PyTorch implementation for training small GPT-style LLMs from scratch, featuring flash attention, RMSNorm, SwiGLU, RoPE, and modern sampling techniques. It includes a full training pipeline with dataset preprocessing, SentencePiece tokenizer training, and text generation sampling, aimed at education.", "when_to_avoid": ["you need production-grade LLM training at scale with distributed support", "you want a ready-made large pretrained model for real applications", "you need multi-GPU or multi-node training out of the box"], "when_to_choose": ["you want a readable, minimal codebase to learn LLM training internals", "you need to train a small GPT on a custom dataset with a modern GPU", "you want an educational alternative to heavyweight frameworks like nanoGPT"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/smolgpt", "repo": "Om-Alve/smolGPT", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:34:29.825130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2ca6c477dd5d48900da99ca58b885e196289f11d60de06b019847d2c449507d", "fetched_at": "2026-08-28T04:04:49.793759+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Om-Alve/smolGPT"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:34:29.825130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2ca6c477dd5d48900da99ca58b885e196289f11d60de06b019847d2c449507d", "fetched_at": "2026-08-28T04:04:49.793759+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Om-Alve/smolGPT"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:34:29.825130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2ca6c477dd5d48900da99ca58b885e196289f11d60de06b019847d2c449507d", "fetched_at": "2026-08-28T04:04:49.793759+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Om-Alve/smolGPT"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:34:29.825130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2ca6c477dd5d48900da99ca58b885e196289f11d60de06b019847d2c449507d", "fetched_at": "2026-08-28T04:04:49.793759+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Om-Alve/smolGPT"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:34:29.825130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2ca6c477dd5d48900da99ca58b885e196289f11d60de06b019847d2c449507d", "fetched_at": "2026-08-28T04:04:49.793759+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Om-Alve/smolGPT"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:34:29.825130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2ca6c477dd5d48900da99ca58b885e196289f11d60de06b019847d2c449507d", "fetched_at": "2026-08-28T04:04:49.793759+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Om-Alve/smolGPT"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.793759+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:34:29.825130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2ca6c477dd5d48900da99ca58b885e196289f11d60de06b019847d2c449507d", "fetched_at": "2026-08-28T04:04:49.793759+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Om-Alve/smolGPT"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:34:29.825130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2ca6c477dd5d48900da99ca58b885e196289f11d60de06b019847d2c449507d", "fetched_at": "2026-08-28T04:04:49.793759+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Om-Alve/smolGPT"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:34:29.825130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2ca6c477dd5d48900da99ca58b885e196289f11d60de06b019847d2c449507d", "fetched_at": "2026-08-28T04:04:49.793759+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Om-Alve/smolGPT"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:34:29.825130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2ca6c477dd5d48900da99ca58b885e196289f11d60de06b019847d2c449507d", "fetched_at": "2026-08-28T04:04:49.793759+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Om-Alve/smolGPT"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 6, "longevity": 42, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 598, "days_push": 564, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}