{"adoption": {"forks": 167, "observed_at": "2026-08-28T04:06:58.545358+00:00", "stars": 2526}, "canonical_url": "https://ross.abutalabs.com/products/awesome-llm-post-training", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Awesome Reasoning LLM Tutorial/Survey/Guide", "domain": ["large-language-models", "artificial-intelligence", "tutorials", "awesome-lists", "reinforcement-learning"], "enriched": true, "function": ["llm-training", "machine-learning", "documentation"], "health_score": 77, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["mbzuai-oryx/Awesome-LLM-Post-training"], "name": "mbzuai-oryx/Awesome-LLM-Post-training", "platform": ["python"], "pushed_at": "2026-07-27T13:26:23+00:00", "repo": "mbzuai-oryx/Awesome-LLM-Post-training", "stars": 2526, "tags": ["post-training", "reasoning", "fine-tuning", "reinforcement-learning", "test-time-scaling", "survey", "curated-list", "rlhf"], "topics": ["fine", "large-language-models", "post-training", "reasoning", "reinforcement-learning", "scaling"], "urls": [], "use_cases": ["find papers on LLM post-training techniques", "learn about reasoning LLM methods like RLHF and test-time scaling", "survey fine-tuning and reinforcement learning approaches for LLMs", "find benchmarks for reasoning large language models", "keep up with new research on LLM reasoning", "prepare a literature review on post-training LLMs"], "what_it_is": "A curated awesome-list and survey companion collecting papers, code, benchmarks, and resources on LLM post-training methodologies, organized into fine-tuning, reinforcement learning, and test-time scaling. It accompanies a TPAMI-accepted survey paper on reasoning large language models.", "when_to_avoid": ["you need runnable training code or a production training framework", "you want a hands-on tutorial with step-by-step exercises rather than a paper list", "you need a maintained software library with releases"], "when_to_choose": ["you need a curated, taxonomy-organized reading list on LLM post-training", "you are researching reasoning models, RLHF, or test-time scaling", "you want the companion resources for the TPAMI/arXiv survey paper"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/awesome-llm-post-training", "repo": "mbzuai-oryx/Awesome-LLM-Post-training", "role": "main", "score": 63}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:25:29.084874+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4216892aab4410bafaf077d5b69caa34a5273dc9f34a74cfa9dbecb473f286b7", "fetched_at": "2026-08-28T04:06:58.545358+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mbzuai-oryx/Awesome-LLM-Post-training"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:25:29.084874+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4216892aab4410bafaf077d5b69caa34a5273dc9f34a74cfa9dbecb473f286b7", "fetched_at": "2026-08-28T04:06:58.545358+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mbzuai-oryx/Awesome-LLM-Post-training"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:25:29.084874+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4216892aab4410bafaf077d5b69caa34a5273dc9f34a74cfa9dbecb473f286b7", "fetched_at": "2026-08-28T04:06:58.545358+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mbzuai-oryx/Awesome-LLM-Post-training"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:25:29.084874+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4216892aab4410bafaf077d5b69caa34a5273dc9f34a74cfa9dbecb473f286b7", "fetched_at": "2026-08-28T04:06:58.545358+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mbzuai-oryx/Awesome-LLM-Post-training"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:25:29.084874+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4216892aab4410bafaf077d5b69caa34a5273dc9f34a74cfa9dbecb473f286b7", "fetched_at": "2026-08-28T04:06:58.545358+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mbzuai-oryx/Awesome-LLM-Post-training"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:25:29.084874+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4216892aab4410bafaf077d5b69caa34a5273dc9f34a74cfa9dbecb473f286b7", "fetched_at": "2026-08-28T04:06:58.545358+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mbzuai-oryx/Awesome-LLM-Post-training"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:58.545358+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:25:29.084874+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4216892aab4410bafaf077d5b69caa34a5273dc9f34a74cfa9dbecb473f286b7", "fetched_at": "2026-08-28T04:06:58.545358+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mbzuai-oryx/Awesome-LLM-Post-training"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:25:29.084874+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4216892aab4410bafaf077d5b69caa34a5273dc9f34a74cfa9dbecb473f286b7", "fetched_at": "2026-08-28T04:06:58.545358+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mbzuai-oryx/Awesome-LLM-Post-training"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:25:29.084874+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4216892aab4410bafaf077d5b69caa34a5273dc9f34a74cfa9dbecb473f286b7", "fetched_at": "2026-08-28T04:06:58.545358+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mbzuai-oryx/Awesome-LLM-Post-training"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:25:29.084874+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4216892aab4410bafaf077d5b69caa34a5273dc9f34a74cfa9dbecb473f286b7", "fetched_at": "2026-08-28T04:06:58.545358+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mbzuai-oryx/Awesome-LLM-Post-training"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 94, "longevity": 40, "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": 566, "days_push": 37, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 63, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}