{"version":"mdrss-hashtag-feed/1","tag":"training-fine-tuning","urls":{"html":"https://mdrss.com/feeds/training-fine-tuning","rss":"https://mdrss.com/feeds/training-fine-tuning/rss.xml","json":"https://mdrss.com/feeds/training-fine-tuning/feed.json","markdown":"https://mdrss.com/feeds/training-fine-tuning/index.md"},"updated_at":"2026-08-04T13:54:51.641Z","items":[{"schema":"mdrss.card-summary/v1","id":901379,"version":1,"title":"VLM Collators, Dataset Format, and Pitfalls","annotation":"Full detail backing the summary in SKILL.md. Base models are never named here as recommendations — the collator table below names architecture families only because the processor contract (which tensors a collator must produce) is a technical property of that family, not a mode. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","dataset","format","collator","vlm","collators","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901379","permalink_url":"https://mdrss.com/m/901379","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901379/901379.md","file_url":"https://mdrss.com/api/v1/cards/901379/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901379/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901379/embed","edit_url":"https://mdrss.com/cards/901379/edit","legacy_url":"https://mdrss.com/s/llm-engineering/vlm-collators-dataset-format-and-pitfalls-collider-d435e165ec90"}},{"schema":"mdrss.card-summary/v1","id":901378,"version":1,"title":"Vision-Language SFT","annotation":"This skill assumes finetuning-method-selection already routed here: the data shape is image+text demonstrations, not preference pairs or a verifiable reward signal, and the base is a vision-language model rather than a text-only one. lora-qlora-recipes covers the text-only Lo. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","vision-language","sft","model","text-only","training","fine-tuning","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901378","permalink_url":"https://mdrss.com/m/901378","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901378/901378.md","file_url":"https://mdrss.com/api/v1/cards/901378/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901378/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901378/embed","edit_url":"https://mdrss.com/cards/901378/edit","legacy_url":"https://mdrss.com/s/llm-engineering/vision-language-sft-collider-57bdd13d8871"}},{"schema":"mdrss.card-summary/v1","id":901377,"version":1,"title":"Conversion Recipes","annotation":"Concrete JSONL-to-JSONL conversions for every pattern in SKILL.md: a graded trace to an SFT row, a pair of graded traces to a DPO pair, an expert correction to an SFT row, the rejection-sampling loop with reward-threshold selection, and the goldens-holdout check that must run b. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","graded","sft","pair","conversion","recipes","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901377","permalink_url":"https://mdrss.com/m/901377","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901377/901377.md","file_url":"https://mdrss.com/api/v1/cards/901377/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901377/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901377/embed","edit_url":"https://mdrss.com/cards/901377/edit","legacy_url":"https://mdrss.com/s/llm-engineering/conversion-recipes-collider-aae456a0682b"}},{"schema":"mdrss.card-summary/v1","id":901376,"version":1,"title":"Trace To Training Data","annotation":"This skill assumes eval-harness-first already graded the traces being converted here — goldens, graders, and runs//results.json all exist before conversion starts. This is the flywheel edge that skill names in its own flow: \"the same labeled traces become the training set.\" C. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","traces","training","trace","data","skill","fine-tuning","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901376","permalink_url":"https://mdrss.com/m/901376","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901376/901376.md","file_url":"https://mdrss.com/api/v1/cards/901376/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901376/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901376/embed","edit_url":"https://mdrss.com/cards/901376/edit","legacy_url":"https://mdrss.com/s/llm-engineering/trace-to-training-data-collider-585d0840341a"}},{"schema":"mdrss.card-summary/v1","id":901375,"version":1,"title":"Export Commands","annotation":"Complete command sequences for every format on the SKILL.md Format Map, plus the smoke-test script skeleton. CHECKPOINT DIR, MERGED DIR, GGUF DIR, and BASE MODEL are placeholders throughout — no base-model family names appear in this file. Fill each with the promoted ch. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","export","dir","commands","format","smoke-test","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901375","permalink_url":"https://mdrss.com/m/901375","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901375/901375.md","file_url":"https://mdrss.com/api/v1/cards/901375/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901375/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901375/embed","edit_url":"https://mdrss.com/cards/901375/edit","legacy_url":"https://mdrss.com/s/llm-engineering/export-commands-collider-3d010d813d46"}},{"schema":"mdrss.card-summary/v1","id":901374,"version":1,"title":"Quantized Export","annotation":"The last stop after checkpoint-promotion hands off a PROMOTE verdict: a checkpoint that cleared the four-stage gate still isn't deployed until it's exported in the right format for its target runtime and proven to still work post-export. A REJECT verdict never reaches this. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","quantized","export","verdict","still","format","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901374","permalink_url":"https://mdrss.com/m/901374","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901374/901374.md","file_url":"https://mdrss.com/api/v1/cards/901374/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901374/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901374/embed","edit_url":"https://mdrss.com/cards/901374/edit","legacy_url":"https://mdrss.com/s/llm-engineering/quantized-export-collider-ddf40eb71cf5"}},{"schema":"mdrss.card-summary/v1","id":901373,"version":1,"title":"Preference Optimization","annotation":"This skill assumes finetuning-method-selection already routed here because the data shape is preference pairs or unpaired thumbs-up/down feedback, not demonstrations (that's lora-qlora-recipes) or a verifiable reward signal (that's grpo-rlvr-training). What follows is metho. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","preference","optimization","training","fine-tuning","llm","ml","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901373","permalink_url":"https://mdrss.com/m/901373","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901373/901373.md","file_url":"https://mdrss.com/api/v1/cards/901373/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901373/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901373/embed","edit_url":"https://mdrss.com/cards/901373/edit","legacy_url":"https://mdrss.com/s/llm-engineering/preference-optimization-collider-b169aea710d8"}},{"schema":"mdrss.card-summary/v1","id":901372,"version":1,"title":"Unsloth ↔ TRL/PEFT Mapping","annotation":"Unsloth is a fast-kernel wrapper over PEFT and TRL, not a replacement API — every Unsloth kwarg below has a plain TRL/PEFT equivalent. Use this table to translate an Unsloth config to plain TRL (or back), and to know which knob lives on which object in the current TRL API. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","trl","unsloth","peft","mapping","plain","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901372","permalink_url":"https://mdrss.com/m/901372","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901372/901372.md","file_url":"https://mdrss.com/api/v1/cards/901372/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901372/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901372/embed","edit_url":"https://mdrss.com/cards/901372/edit","legacy_url":"https://mdrss.com/s/llm-engineering/unsloth-trl-peft-mapping-collider-44e8f9d48b10"}},{"schema":"mdrss.card-summary/v1","id":901371,"version":1,"title":"LoRA/QLoRA Hyperparameter Tables","annotation":"Full tables and a complete worked config backing the summary in SKILL.md. Base models are never named here — every example is labeled by size class only; see finetuning-method-selection's references/model-catalog.md for which actual model to use at a given size class. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","tables","lora","qlora","hyperparameter","worked","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901371","permalink_url":"https://mdrss.com/m/901371","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901371/901371.md","file_url":"https://mdrss.com/api/v1/cards/901371/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901371/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901371/embed","edit_url":"https://mdrss.com/cards/901371/edit","legacy_url":"https://mdrss.com/s/llm-engineering/lora-qlora-hyperparameter-tables-collider-b14342469af5"}},{"schema":"mdrss.card-summary/v1","id":901370,"version":1,"title":"LoRA & QLoRA Recipes","annotation":"This skill assumes the routing decision already happened — finetuning-method-selection should have already pointed here because the data shape is demonstrations (SFT), not preference pairs or a verifiable reward signal. What follows is the current best-practice recipe for confi. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","lora","qlora","recipes","already","recipe","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901370","permalink_url":"https://mdrss.com/m/901370","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901370/901370.md","file_url":"https://mdrss.com/api/v1/cards/901370/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901370/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901370/embed","edit_url":"https://mdrss.com/cards/901370/edit","legacy_url":"https://mdrss.com/s/llm-engineering/lora-qlora-recipes-collider-0d338a7b6ec6"}},{"schema":"mdrss.card-summary/v1","id":901369,"version":1,"title":"GRPO Reward Function Library","annotation":"Complete, runnable reward functions for TRL's GRPOTrainer. Every function here follows the current TRL reward-function signature: it accepts completions plus any extra dataset columns as keyword arguments, and returns a list[float] the same length as completions. Base mod. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","reward","function","correctness","grpo","library","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901369","permalink_url":"https://mdrss.com/m/901369","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901369/901369.md","file_url":"https://mdrss.com/api/v1/cards/901369/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901369/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901369/embed","edit_url":"https://mdrss.com/cards/901369/edit","legacy_url":"https://mdrss.com/s/llm-engineering/grpo-reward-function-library-collider-a43d7fc781e8"}},{"schema":"mdrss.card-summary/v1","id":901368,"version":1,"title":"GRPO & RLVR Training","annotation":"This skill assumes finetuning-method-selection already routed here because the target behavior has a verifiable pass/fail signal — not demonstrations (lora-qlora-recipes) or preference pairs (preference-optimization). What follows is when RL is the right tool, the reference. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","grpo","rlvr","training","fine-tuning","llm","ml","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901368","permalink_url":"https://mdrss.com/m/901368","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901368/901368.md","file_url":"https://mdrss.com/api/v1/cards/901368/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901368/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901368/embed","edit_url":"https://mdrss.com/cards/901368/edit","legacy_url":"https://mdrss.com/s/llm-engineering/grpo-rlvr-training-collider-204e909c2dea"}},{"schema":"mdrss.card-summary/v1","id":901367,"version":1,"title":"Memory Math","annotation":"Last verified: 2026-07-13 — refresh when a new size-class anchor is validated or optimizer/dtype defaults change. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","qlora","b-class","memory","math","anchor","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901367","permalink_url":"https://mdrss.com/m/901367","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901367/901367.md","file_url":"https://mdrss.com/api/v1/cards/901367/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901367/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901367/embed","edit_url":"https://mdrss.com/cards/901367/edit","legacy_url":"https://mdrss.com/s/llm-engineering/memory-math-collider-660857d0e2a3"}},{"schema":"mdrss.card-summary/v1","id":901366,"version":1,"title":"Fine-Tuning Method Selection","annotation":"This is the router skill for the fine-tuning lifecycle: it decides whether fine-tuning is the right tool at all, and if so, which method and which base-model size class. Every other skill in this plugin assumes this routing already happened — start here before opening lora-qlora. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","fine-tuning","method","routing","selection","skill","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901366","permalink_url":"https://mdrss.com/m/901366","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901366/901366.md","file_url":"https://mdrss.com/api/v1/cards/901366/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901366/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901366/embed","edit_url":"https://mdrss.com/cards/901366/edit","legacy_url":"https://mdrss.com/s/llm-engineering/fine-tuning-method-selection-collider-56e399856482"}},{"schema":"mdrss.card-summary/v1","id":901365,"version":1,"title":"Judge Calibration Protocol","annotation":"The full procedure behind SKILL.md's \"Judge Calibration Is a Prerequisite\" section. Any grader routed to an LLM-judge follows this before its verdicts count toward a pass rate or a checkpoint promotion decision. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","judge","calibration","protocol","training","fine-tuning","llm","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901365","permalink_url":"https://mdrss.com/m/901365","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901365/901365.md","file_url":"https://mdrss.com/api/v1/cards/901365/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901365/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901365/embed","edit_url":"https://mdrss.com/cards/901365/edit","legacy_url":"https://mdrss.com/s/llm-engineering/judge-calibration-protocol-collider-1a55fc8178e8"}},{"schema":"mdrss.card-summary/v1","id":901364,"version":1,"title":"Grader Templates","annotation":"Runnable examples for the four grader shapes named in SKILL.md's Graders section: schema-compliance, exact-match with normalization, execution-based, and LLM-judge. Every grader returns a binary pass/fail — never a Likert score — per the plugin-wide rule. Wire each one to exact. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","grader","templates","normalization","execution-based","exact","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901364","permalink_url":"https://mdrss.com/m/901364","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901364/901364.md","file_url":"https://mdrss.com/api/v1/cards/901364/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901364/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901364/embed","edit_url":"https://mdrss.com/cards/901364/edit","legacy_url":"https://mdrss.com/s/llm-engineering/grader-templates-collider-52d4a9c8ca32"}},{"schema":"mdrss.card-summary/v1","id":901363,"version":1,"title":"Eval Harness First","annotation":"The Phase 0 gate for the whole plugin: finetuning-method-selection and every downstream skill assume this harness exists before a training config gets written. The harness is not a run-end side artifact — it is the data-curation engine. The same labeled traces that build the go. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","harness","eval","first","phase","gate","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901363","permalink_url":"https://mdrss.com/m/901363","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901363/901363.md","file_url":"https://mdrss.com/api/v1/cards/901363/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901363/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901363/embed","edit_url":"https://mdrss.com/cards/901363/edit","legacy_url":"https://mdrss.com/s/llm-engineering/eval-harness-first-collider-17827f7fffba"}},{"schema":"mdrss.card-summary/v1","id":901362,"version":1,"title":"Synthetic Data: Generation, Filtering, Distillation","annotation":"Full detail backing SKILL.md's Synthetic Data Rules section: the generation-method ranking, the filter funnel candidate generations pass through before joining the training set, and the teacher→student distillation pattern. Base models are never named as recommendations here. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","distillation","synthetic","data","generation","filtering","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901362","permalink_url":"https://mdrss.com/m/901362","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901362/901362.md","file_url":"https://mdrss.com/api/v1/cards/901362/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901362/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901362/embed","edit_url":"https://mdrss.com/cards/901362/edit","legacy_url":"https://mdrss.com/s/llm-engineering/synthetic-data-generation-filtering-distillation-collider-5da5dd48aefa"}},{"schema":"mdrss.card-summary/v1","id":901361,"version":1,"title":"Dataset Formats and Template Application","annotation":"Concrete JSONL examples for every format in SKILL.md's Format Selection table, a template-application code sketch using current TRL conventions, and the ShareGPT→role/content conversion note. Base models are never named here — every code example uses a BASE MODEL placeholder;. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","template","dataset","formats","application","every","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901361","permalink_url":"https://mdrss.com/m/901361","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901361/901361.md","file_url":"https://mdrss.com/api/v1/cards/901361/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901361/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901361/embed","edit_url":"https://mdrss.com/cards/901361/edit","legacy_url":"https://mdrss.com/s/llm-engineering/dataset-formats-and-template-application-collider-4ec7ba06fca2"}},{"schema":"mdrss.card-summary/v1","id":901360,"version":1,"title":"Dataset Curation","annotation":"This skill assumes finetuning-method-selection already routed here — the next step is preparing data, not choosing a method. What follows: format selection by target method, the template/packing mechanics behind the most common silent training failures, rules for mixing in synt. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","dataset","curation","data","format","selection","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901360","permalink_url":"https://mdrss.com/m/901360","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901360/901360.md","file_url":"https://mdrss.com/api/v1/cards/901360/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901360/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901360/embed","edit_url":"https://mdrss.com/cards/901360/edit","legacy_url":"https://mdrss.com/s/llm-engineering/dataset-curation-collider-b025ad8a03e4"}},{"schema":"mdrss.card-summary/v1","id":901359,"version":1,"title":"Gate Templates","annotation":"Complete promotion-report.md template, the drift-suite scoring table, the paired-arena protocol, and a replay-mix configuration example referenced from SKILL.md. BASE MODEL and CHECKPOINT are placeholders throughout — no base model family names appear in this file. Benchm. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","example","gate","templates","promotion-report.md","template","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901359","permalink_url":"https://mdrss.com/m/901359","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901359/901359.md","file_url":"https://mdrss.com/api/v1/cards/901359/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901359/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901359/embed","edit_url":"https://mdrss.com/cards/901359/edit","legacy_url":"https://mdrss.com/s/llm-engineering/gate-templates-collider-2ba7f19b7b30"}},{"schema":"mdrss.card-summary/v1","id":901358,"version":1,"title":"Checkpoint Promotion","annotation":"The Phase 5 gate for the whole plugin: a checkpoint that trains cleanly and beats its task metric still doesn't ship without clearing all four stages below. eval-harness-first built the suite re-run here — this skill is where that suite's baseline decides something. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","checkpoint","promotion","gate","suite","training","fine-tuning","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901358","permalink_url":"https://mdrss.com/m/901358","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901358/901358.md","file_url":"https://mdrss.com/api/v1/cards/901358/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901358/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901358/embed","edit_url":"https://mdrss.com/cards/901358/edit","legacy_url":"https://mdrss.com/s/llm-engineering/checkpoint-promotion-collider-cc3b4d3a8066"}},{"schema":"mdrss.card-summary/v1","id":901357,"version":1,"title":"Fine-tune for: $ARGUMENTS","annotation":"This command orchestrates the eval-gated fine-tuning lifecycle across seven phases, each owned by a specialist agent and gated by the artifact the prior phase produced:. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","phase","fine-tune","arguments","training","fine-tuning","llm","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901357","permalink_url":"https://mdrss.com/m/901357","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901357/901357.md","file_url":"https://mdrss.com/api/v1/cards/901357/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901357/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901357/embed","edit_url":"https://mdrss.com/cards/901357/edit","legacy_url":"https://mdrss.com/s/llm-engineering/fine-tune-for-arguments-collider-6bd3e8fdac82"}},{"schema":"mdrss.card-summary/v1","id":901356,"version":1,"title":"Llm finetuning training engineer","annotation":"You are the fine-tuning training engineer: the workhorse who takes a training-brief.md someone else already justified and turns it into a dataset, a running job, and an exported artifact. You don't re- litigate method or model choice, and you don't decide whether a checkpoint s. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","phase","training","dataset","don","fine-tuning","llm","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901356","permalink_url":"https://mdrss.com/m/901356","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901356/901356.md","file_url":"https://mdrss.com/api/v1/cards/901356/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901356/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901356/embed","edit_url":"https://mdrss.com/cards/901356/edit","legacy_url":"https://mdrss.com/s/llm-engineering/llm-finetuning-training-engineer-collider-9d40accca00d"}},{"schema":"mdrss.card-summary/v1","id":901355,"version":1,"title":"Llm finetuning eval engineer","annotation":"You are the fine-tuning eval engineer: the independent gatekeeper who builds the measuring stick before anyone trains against it, and reads that same measuring stick to decide whether a trained checkpoint ships. You own the two phases that bound the lifecycle — Phase 0 before a t. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","phase","measuring","stick","checkpoint","training","fine-tuning","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901355","permalink_url":"https://mdrss.com/m/901355","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901355/901355.md","file_url":"https://mdrss.com/api/v1/cards/901355/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901355/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901355/embed","edit_url":"https://mdrss.com/cards/901355/edit","legacy_url":"https://mdrss.com/s/llm-engineering/llm-finetuning-eval-engineer-collider-752bf5343139"}},{"schema":"mdrss.card-summary/v1","id":901354,"version":1,"title":"Llm finetuning architect","annotation":"You are the fine-tuning architect: a skeptical strategist who decides whether fine-tuning is the right tool at all before anyone opens a training config. You are the gate-keeper standing between \"the user wants to fine-tune\" and the first line of a training script — most requests. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","fine-tuning","training","llm","ml","engineering","agent-playbook","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:43.738Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901354","permalink_url":"https://mdrss.com/m/901354","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901354/901354.md","file_url":"https://mdrss.com/api/v1/cards/901354/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901354/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901354/embed","edit_url":"https://mdrss.com/cards/901354/edit","legacy_url":"https://mdrss.com/s/llm-engineering/llm-finetuning-architect-collider-13c52cf04946"}},{"schema":"mdrss.card-summary/v1","id":901107,"version":1,"title":"LLM (Large Language Models) FineTuning Projects and notes on common practical techniques","annotation":"logo]: https://github.com/rohan-paul/rohan-paul/blob/master/assets/png. Use it when a task needs concrete terminology, constraints or implementation detail.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"reference","tags":["llm-ml-engineering","training-fine-tuning","llm","language","models","techniques","large","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:05.624Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901107","permalink_url":"https://mdrss.com/m/901107","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901107/901107.md","file_url":"https://mdrss.com/api/v1/cards/901107/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901107/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901107/embed","edit_url":"https://mdrss.com/cards/901107/edit","legacy_url":"https://mdrss.com/s/llm-engineering/llm-large-language-models-finetuning-projects-and-notes-on-common-prac-collider-b4b3a2d9231d"}},{"schema":"mdrss.card-summary/v1","id":901097,"version":1,"title":"What is a good dataset?","annotation":"A curated reference on training & fine-tuning centered on What is a good dataset?. Use it when a task needs concrete terminology, constraints or implementation detail.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"reference","tags":["llm-ml-engineering","training-fine-tuning","data","dataset","good","datasets","tools","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:04.205Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901097","permalink_url":"https://mdrss.com/m/901097","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901097/901097.md","file_url":"https://mdrss.com/api/v1/cards/901097/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901097/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901097/embed","edit_url":"https://mdrss.com/cards/901097/edit","legacy_url":"https://mdrss.com/s/llm-engineering/what-is-a-good-dataset-collider-6b7d3406f684"}},{"schema":"mdrss.card-summary/v1","id":901088,"version":1,"title":"Synthetic Data Kit","annotation":"Tool for generating high-quality synthetic datasets to fine-tune LLMs. Use it to navigate the topic and choose relevant methods, papers or tools.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"reference","tags":["llm-ml-engineering","training-fine-tuning","processing","synthetic","data","kit","tool","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:04.205Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901088","permalink_url":"https://mdrss.com/m/901088","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901088/901088.md","file_url":"https://mdrss.com/api/v1/cards/901088/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901088/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901088/embed","edit_url":"https://mdrss.com/cards/901088/edit","legacy_url":"https://mdrss.com/s/llm-engineering/synthetic-data-kit-collider-ade88a6166ee"}},{"schema":"mdrss.card-summary/v1","id":901032,"version":1,"title":"SAM3-LoRA: Efficient Fine-Tuning with Low-Rank Adaptation","annotation":"Quick Start • Architecture • Training • Validation • Inference • Examples • Configuration • Troubleshooting. Use it to ground design choices in named patterns, trade-offs and examples.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"reference","tags":["llm-ml-engineering","training-fine-tuning","training","sam3-lora","efficient","fine-tuning","low-rank","llm","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:47:59.231Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901032","permalink_url":"https://mdrss.com/m/901032","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901032/901032.md","file_url":"https://mdrss.com/api/v1/cards/901032/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901032/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901032/embed","edit_url":"https://mdrss.com/cards/901032/edit","legacy_url":"https://mdrss.com/s/llm-engineering/sam3-lora-efficient-fine-tuning-with-low-rank-adaptation-collider-41e68677ef7c"}}]}