{"adoption": {"forks": 226, "observed_at": "2026-08-28T04:04:45.483113+00:00", "stars": 1448}, "canonical_url": "https://ross.abutalabs.com/products/bigscience", "card": {"archived": false, "artifact_type": "library", "description": "Ongoing research training transformer language models at scale, including: BERT & GPT-2", "domain": ["large-language-models", "deep-learning", "machine-learning", "gpu-computing"], "enriched": true, "function": ["llm-training", "deep-learning", "machine-learning", "benchmarking"], "health_score": 20, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["bigscience-workshop/Megatron-DeepSpeed", "bigscience-workshop/bigscience"], "name": "BigScience", "platform": ["python"], "pushed_at": "2024-03-20T16:10:21+00:00", "repo": "bigscience-workshop/Megatron-DeepSpeed", "stars": 1448, "tags": ["megatron-lm", "deepspeed", "distributed-training", "transformer-models", "research-project", "gpt", "bert", "hpc", "linux", "gpu", "docker"], "topics": [], "urls": [], "use_cases": ["pretrain large GPT-style language models on GPU clusters", "train BERT models with distributed DeepSpeed training", "fine-tune pretrained transformer language models", "run zero-shot evaluation of large language models", "generate text with pretrained transformer checkpoints", "set up multi-node distributed LLM training pipelines"], "what_it_is": "BigScience is a research project training large transformer language models (BERT, GPT-style) at scale, built on a fork of Megatron-LM integrated with DeepSpeed. The repository provides training scripts, documentation, and tooling for distributed multi-GPU pretraining and fine-tuning of large language models.", "when_to_avoid": ["you just want to run inference with an existing LLM rather than train one", "you need a maintained, actively developed training framework", "you lack access to NVIDIA GPU clusters or multi-node HPC infrastructure", "you want a simple high-level API like Hugging Face Trainer"], "when_to_choose": ["you need to pretrain or fine-tune large transformer LMs across many GPUs or nodes", "you want Megatron-LM's efficiency combined with DeepSpeed's memory optimizations", "you're reproducing BigScience-style open collaborative LLM training experiments"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/repos/bigscience-workshop/Megatron-DeepSpeed", "repo": "bigscience-workshop/Megatron-DeepSpeed", "role": "main", "score": 32}, {"path": "/repos/bigscience-workshop/bigscience", "repo": "bigscience-workshop/bigscience", "role": "docs", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:36:02.237951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e60193541138be48dfd1b95a5dde85f40c9b27830a0a25f27eb4edd8314b199", "fetched_at": "2026-08-28T04:04:45.483113+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigscience-workshop/Megatron-DeepSpeed"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:36:02.237951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e60193541138be48dfd1b95a5dde85f40c9b27830a0a25f27eb4edd8314b199", "fetched_at": "2026-08-28T04:04:45.483113+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigscience-workshop/Megatron-DeepSpeed"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:36:02.237951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e60193541138be48dfd1b95a5dde85f40c9b27830a0a25f27eb4edd8314b199", "fetched_at": "2026-08-28T04:04:45.483113+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigscience-workshop/Megatron-DeepSpeed"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:36:02.237951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e60193541138be48dfd1b95a5dde85f40c9b27830a0a25f27eb4edd8314b199", "fetched_at": "2026-08-28T04:04:45.483113+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigscience-workshop/Megatron-DeepSpeed"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:36:02.237951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e60193541138be48dfd1b95a5dde85f40c9b27830a0a25f27eb4edd8314b199", "fetched_at": "2026-08-28T04:04:45.483113+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigscience-workshop/Megatron-DeepSpeed"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:36:02.237951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e60193541138be48dfd1b95a5dde85f40c9b27830a0a25f27eb4edd8314b199", "fetched_at": "2026-08-28T04:04:45.483113+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigscience-workshop/Megatron-DeepSpeed"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.483113+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:36:02.237951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e60193541138be48dfd1b95a5dde85f40c9b27830a0a25f27eb4edd8314b199", "fetched_at": "2026-08-28T04:04:45.483113+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigscience-workshop/Megatron-DeepSpeed"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:36:02.237951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e60193541138be48dfd1b95a5dde85f40c9b27830a0a25f27eb4edd8314b199", "fetched_at": "2026-08-28T04:04:45.483113+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigscience-workshop/Megatron-DeepSpeed"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:36:02.237951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e60193541138be48dfd1b95a5dde85f40c9b27830a0a25f27eb4edd8314b199", "fetched_at": "2026-08-28T04:04:45.483113+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigscience-workshop/Megatron-DeepSpeed"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:36:02.237951+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e60193541138be48dfd1b95a5dde85f40c9b27830a0a25f27eb4edd8314b199", "fetched_at": "2026-08-28T04:04:45.483113+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigscience-workshop/Megatron-DeepSpeed"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1888, "days_push": 896, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}