{"version":"mdrss-catalog-feed/1","domain":{"slug":"llm-engineering","label":"LLM Engineering","description":"Training, tuning, serving and evaluating language models."},"feeds":[{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"}],"urls":{"html":"https://mdrss.com/catalog/llm-engineering","rss":"https://mdrss.com/catalog/llm-engineering/rss.xml","json":"https://mdrss.com/catalog/llm-engineering/feed.json","markdown":"https://mdrss.com/catalog/llm-engineering/index.md"},"updated_at":"2026-08-04T13:54:51.641Z","items":[{"id":901385,"title":"Recsys Pipeline Architect","annotation":"A spec-and-scaffold skill for building composable recommendation, ranking, and feed pipelines. Encodes the six-stage pattern popularized by xAI's open-sourced For You algorithm (Apache 2.0) and applies it to any \"top K for (user, context)\" problem. Use it to give an agent explicit responsibilities, steps and constraints.","feed":"llm-engineering","semantic_path":"llm-engineering:mlops-and-ml-systems","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901385","permalink_url":"https://mdrss.com/m/901385","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901385/901385.md","file_url":"https://mdrss.com/api/v1/cards/901385/file","raw_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901385/raw","embed_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901385/embed","edit_url":"https://mdrss.com/cards/901385/edit","legacy_url":"https://mdrss.com/s/llm-engineering/recsys-pipeline-architect-collider-aedb43f2b3a6"},{"id":901384,"title":"ML Pipeline Workflow","annotation":"Complete end-to-end MLOps pipeline orchestration from data preparation through model deployment. Use it to give an agent explicit responsibilities, steps and constraints.","feed":"llm-engineering","semantic_path":"llm-engineering:mlops-and-ml-systems","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901384","permalink_url":"https://mdrss.com/m/901384","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901384/901384.md","file_url":"https://mdrss.com/api/v1/cards/901384/file","raw_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901384/raw","embed_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901384/embed","edit_url":"https://mdrss.com/cards/901384/edit","legacy_url":"https://mdrss.com/s/llm-engineering/ml-pipeline-workflow-collider-c69981cadf0d"},{"id":901383,"title":"Machine Learning Pipeline - Multi-Agent MLOps Orchestration","annotation":"This workflow orchestrates multiple specialized agents to build a production-ready ML pipeline following modern MLOps best practices. The approach emphasizes:. Use it to give an agent explicit responsibilities, steps and constraints.","feed":"llm-engineering","semantic_path":"llm-engineering:mlops-and-ml-systems","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901383","permalink_url":"https://mdrss.com/m/901383","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901383/901383.md","file_url":"https://mdrss.com/api/v1/cards/901383/file","raw_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901383/raw","embed_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901383/embed","edit_url":"https://mdrss.com/cards/901383/edit","legacy_url":"https://mdrss.com/s/llm-engineering/machine-learning-pipeline-multi-agent-mlops-orchestration-collider-79c980bc8817"},{"id":901382,"title":"Mlops engineer","annotation":"You are an MLOps engineer specializing in ML infrastructure, automation, and production ML systems across cloud platforms. Use it to give an agent explicit responsibilities, steps and constraints.","feed":"llm-engineering","semantic_path":"llm-engineering:mlops-and-ml-systems","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901382","permalink_url":"https://mdrss.com/m/901382","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901382/901382.md","file_url":"https://mdrss.com/api/v1/cards/901382/file","raw_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901382/raw","embed_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901382/embed","edit_url":"https://mdrss.com/cards/901382/edit","legacy_url":"https://mdrss.com/s/llm-engineering/mlops-engineer-collider-1ab425c93bdb"},{"id":901381,"title":"Ml engineer","annotation":"You are an ML engineer specializing in production machine learning systems, model serving, and ML infrastructure. Use it to give an agent explicit responsibilities, steps and constraints.","feed":"llm-engineering","semantic_path":"llm-engineering:mlops-and-ml-systems","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901381","permalink_url":"https://mdrss.com/m/901381","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901381/901381.md","file_url":"https://mdrss.com/api/v1/cards/901381/file","raw_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901381/raw","embed_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901381/embed","edit_url":"https://mdrss.com/cards/901381/edit","legacy_url":"https://mdrss.com/s/llm-engineering/ml-engineer-collider-1d38ca04d3ff"},{"id":901380,"title":"Data scientist","annotation":"You are a data scientist specializing in advanced analytics, machine learning, statistical modeling, and data-driven business insights. Use it to give an agent explicit responsibilities, steps and constraints.","feed":"llm-engineering","semantic_path":"llm-engineering:mlops-and-ml-systems","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901380","permalink_url":"https://mdrss.com/m/901380","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901380/901380.md","file_url":"https://mdrss.com/api/v1/cards/901380/file","raw_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901380/raw","embed_url":"https://mdrss.com/llm-engineering/mlops-and-ml-systems/901380/embed","edit_url":"https://mdrss.com/cards/901380/edit","legacy_url":"https://mdrss.com/s/llm-engineering/data-scientist-collider-46ffc1d16d67"},{"id":901379,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901378,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901377,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901376,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901375,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901374,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901373,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901372,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901371,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901370,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901369,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901368,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901367,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901366,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901365,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901364,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901363,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901362,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901361,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901360,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901359,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901358,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901357,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901356,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901355,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901354,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901285,"title":"G1: CUDA 12/13 ABI Mismatch","annotation":"Last verified: 2026-07-14 — refresh when CUDA, PyTorch, or the DGX Spark stack ships a new major version. Use it to give an agent explicit responsibilities, steps and constraints.","feed":"llm-engineering","semantic_path":"llm-engineering:inference-and-quantization","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901285","permalink_url":"https://mdrss.com/m/901285","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901285/901285.md","file_url":"https://mdrss.com/api/v1/cards/901285/file","raw_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901285/raw","embed_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901285/embed","edit_url":"https://mdrss.com/cards/901285/edit","legacy_url":"https://mdrss.com/s/llm-engineering/g1-cuda-12-13-abi-mismatch-collider-1687d0b53cda"},{"id":901284,"title":"Spark Training Gotchas","annotation":"DGX Spark's GB10 chip (Grace Blackwell, SM121, 128GB unified memory, aarch64) has ten recurring failure modes across launch, memory, thermals, bandwidth, and precision. Each is named G1–G10 so it can be checked by number — the numbering is load-bearing for tooling that runs these. Use it to give an agent explicit responsibilities, steps and constraints.","feed":"llm-engineering","semantic_path":"llm-engineering:inference-and-quantization","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901284","permalink_url":"https://mdrss.com/m/901284","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901284/901284.md","file_url":"https://mdrss.com/api/v1/cards/901284/file","raw_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901284/raw","embed_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901284/embed","edit_url":"https://mdrss.com/cards/901284/edit","legacy_url":"https://mdrss.com/s/llm-engineering/spark-training-gotchas-collider-04100adf5fb4"},{"id":901281,"title":"Spark Environment Setup","annotation":"DGX Spark ships a GB10 Grace Blackwell chip: aarch64 CPU, SM121 GPU, 128GB unified memory, CUDA 13. This is a narrower and younger platform than a standard x86 CUDA 12 box, so package selection and ABI matching matter more than usual — the wheel ecosystem for aarch64 + CUDA 13 is. Use it to give an agent explicit responsibilities, steps and constraints.","feed":"llm-engineering","semantic_path":"llm-engineering:inference-and-quantization","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901281","permalink_url":"https://mdrss.com/m/901281","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901281/901281.md","file_url":"https://mdrss.com/api/v1/cards/901281/file","raw_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901281/raw","embed_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901281/embed","edit_url":"https://mdrss.com/cards/901281/edit","legacy_url":"https://mdrss.com/s/llm-engineering/spark-environment-setup-collider-ea0823a974ce"},{"id":901240,"title":"Pull Request Enhancement","annotation":"You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descriptions, automate review processes, and ensure PRs follow best practices for clarity, size, and reviewability. Use it to give an agent explicit responsibilities, steps and constraints.","feed":"llm-engineering","semantic_path":"llm-engineering:rag-and-knowledge-systems","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901240","permalink_url":"https://mdrss.com/m/901240","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901240/901240.md","file_url":"https://mdrss.com/api/v1/cards/901240/file","raw_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901240/raw","embed_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901240/embed","edit_url":"https://mdrss.com/cards/901240/edit","legacy_url":"https://mdrss.com/s/llm-engineering/pull-request-enhancement-collider-7a766861741e"},{"id":901107,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"reference","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901104,"title":"PremSQL | Easy to use fully local RAG on Databases","annotation":"PremSQL is an open-source library designed to help developers create secure, fully local Text-to-SQL solutions using small language models. It provides all the essential tools to build and deploy end-to-end Text-to-SQL pipelines with customizable components, making it ideal for s. Use it to build a structured path from fundamentals to hands-on practice.","feed":"llm-engineering","semantic_path":"llm-engineering:rag-and-knowledge-systems","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901104","permalink_url":"https://mdrss.com/m/901104","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901104/901104.md","file_url":"https://mdrss.com/api/v1/cards/901104/file","raw_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901104/raw","embed_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901104/embed","edit_url":"https://mdrss.com/cards/901104/edit","legacy_url":"https://mdrss.com/s/llm-engineering/premsql-easy-to-use-fully-local-rag-on-databases-collider-2a6388c22207"},{"id":901103,"title":"pgvector","annotation":"Plus ACID compliance, point-in-time recovery, JOINs, and all of the other great features of Postgres. Use it to make implementation decisions and avoid common dead ends.","feed":"llm-engineering","semantic_path":"llm-engineering:rag-and-knowledge-systems","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901103","permalink_url":"https://mdrss.com/m/901103","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901103/901103.md","file_url":"https://mdrss.com/api/v1/cards/901103/file","raw_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901103/raw","embed_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901103/embed","edit_url":"https://mdrss.com/cards/901103/edit","legacy_url":"https://mdrss.com/s/llm-engineering/pgvector-collider-28e49852f568"},{"id":901097,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"reference","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901092,"title":"MarkItDown","annotation":"MarkItDown is a lightweight Python utility for converting various files to Markdown for use with LLMs and related text analysis pipelines. To this end, it is most comparable to textract, but with a focus on preserving important document structure and content as Markdown (includin. Use it to build a structured path from fundamentals to hands-on practice.","feed":"llm-engineering","semantic_path":"llm-engineering:rag-and-knowledge-systems","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901092","permalink_url":"https://mdrss.com/m/901092","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901092/901092.md","file_url":"https://mdrss.com/api/v1/cards/901092/file","raw_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901092/raw","embed_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901092/embed","edit_url":"https://mdrss.com/cards/901092/edit","legacy_url":"https://mdrss.com/s/llm-engineering/markitdown-collider-74a528865488"},{"id":901088,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"reference","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901084,"title":"Transfer Engine (TE)","annotation":"Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. Under real workloads, Mooncake’s innovative architecture enables Kimi to handle 75% more requests while adhering to SLOs. Use it to ground design choices in named patterns, trade-offs and examples.","feed":"llm-engineering","semantic_path":"llm-engineering:inference-and-quantization","content_type":"reference","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901084","permalink_url":"https://mdrss.com/m/901084","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901084/901084.md","file_url":"https://mdrss.com/api/v1/cards/901084/file","raw_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901084/raw","embed_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901084/embed","edit_url":"https://mdrss.com/cards/901084/edit","legacy_url":"https://mdrss.com/s/llm-engineering/transfer-engine-te-collider-acfa08d20c74"},{"id":901083,"title":"LLMTools: Run & Finetune LLMs on Consumer GPUs","annotation":"LLMTools is a user-friendly library for running and finetuning LLMs in low-resource settings. Features include: 🔨 LLM finetuning in 2-bit, 3-bit, 4-bit precision using the ModuLoRA algorithm 🐍 Easy-to-use Python API for quantization, inference, and finetuning 🤖 Modular supp. Use it to navigate the topic and choose relevant methods, papers or tools.","feed":"llm-engineering","semantic_path":"llm-engineering:inference-and-quantization","content_type":"reference","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901083","permalink_url":"https://mdrss.com/m/901083","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901083/901083.md","file_url":"https://mdrss.com/api/v1/cards/901083/file","raw_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901083/raw","embed_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901083/embed","edit_url":"https://mdrss.com/cards/901083/edit","legacy_url":"https://mdrss.com/s/llm-engineering/llmtools-run-finetune-llms-on-consumer-gpus-collider-1489dd838684"},{"id":901071,"title":"TRL - Transformers Reinforcement Learning","annotation":"TRL is a cutting-edge library designed for post-training foundation models using advanced techniques like Supervised Fine-Tuning (SFT), Group Relative Policy Optimization (GRPO), and Direct Preference Optimization (DPO). Built on top of the 🤗 Transformers ecosystem, TRL supports. Use it to navigate the topic and choose relevant methods, papers or tools.","feed":"llm-engineering","semantic_path":"llm-engineering:inference-and-quantization","content_type":"reference","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901071","permalink_url":"https://mdrss.com/m/901071","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901071/901071.md","file_url":"https://mdrss.com/api/v1/cards/901071/file","raw_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901071/raw","embed_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901071/embed","edit_url":"https://mdrss.com/cards/901071/edit","legacy_url":"https://mdrss.com/s/llm-engineering/trl-transformers-reinforcement-learning-collider-d07f9474376d"},{"id":901061,"title":"StageRAG: A Framework for Building Hallucination-Resistant RAG Applications","annotation":"StageRAG is a lightweight, production-ready RAG framework designed to give you precise control over the speed-versus-accuracy trade-off. It allows you to build high-factuality applications while gracefully managing uncertainty in LLM responses. Use it to navigate the topic and choose relevant methods, papers or tools.","feed":"llm-engineering","semantic_path":"llm-engineering:rag-and-knowledge-systems","content_type":"reference","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901061","permalink_url":"https://mdrss.com/m/901061","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901061/901061.md","file_url":"https://mdrss.com/api/v1/cards/901061/file","raw_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901061/raw","embed_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901061/embed","edit_url":"https://mdrss.com/cards/901061/edit","legacy_url":"https://mdrss.com/s/llm-engineering/stagerag-a-framework-for-building-hallucination-resistant-rag-applicat-collider-4d1a3640841b"},{"id":901042,"title":"Python Bindings for llama.cpp","annotation":"Simple Python bindings for @ggerganov's llama.cpp library. This package provides:. Use it to ground design choices in named patterns, trade-offs and examples.","feed":"llm-engineering","semantic_path":"llm-engineering:inference-and-quantization","content_type":"reference","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901042","permalink_url":"https://mdrss.com/m/901042","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901042/901042.md","file_url":"https://mdrss.com/api/v1/cards/901042/file","raw_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901042/raw","embed_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901042/embed","edit_url":"https://mdrss.com/cards/901042/edit","legacy_url":"https://mdrss.com/s/llm-engineering/python-bindings-for-llama-cpp-collider-c58e74fe6455"},{"id":901037,"title":"AQLM","annotation":"Official PyTorch implementation for Extreme Compression of Large Language Models via Additive Quantization. Use it to navigate the topic and choose relevant methods, papers or tools.","feed":"llm-engineering","semantic_path":"llm-engineering:inference-and-quantization","content_type":"reference","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901037","permalink_url":"https://mdrss.com/m/901037","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901037/901037.md","file_url":"https://mdrss.com/api/v1/cards/901037/file","raw_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901037/raw","embed_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901037/embed","edit_url":"https://mdrss.com/cards/901037/edit","legacy_url":"https://mdrss.com/s/llm-engineering/aqlm-collider-0adcf7644f16"},{"id":901032,"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.","feed":"llm-engineering","semantic_path":"llm-engineering:training-and-fine-tuning","content_type":"reference","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","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"},{"id":901025,"title":"Advanced RAG Techniques 🚀","annotation":"A community-driven hub of 42+ runnable notebooks covering RAG techniques from foundational to cutting-edge - the intuition, the code, and the references to build more accurate, context-rich retrieval systems. Use it as a repeatable review, validation or hardening pass.","feed":"llm-engineering","semantic_path":"llm-engineering:rag-and-knowledge-systems","content_type":"guide","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901025","permalink_url":"https://mdrss.com/m/901025","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901025/901025.md","file_url":"https://mdrss.com/api/v1/cards/901025/file","raw_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901025/raw","embed_url":"https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901025/embed","edit_url":"https://mdrss.com/cards/901025/edit","legacy_url":"https://mdrss.com/s/llm-engineering/advanced-rag-techniques-collider-e4ba181f0065"},{"id":901001,"title":"Awesome Model Quantization","annotation":"This repo collects papers, documents, and codes about model quantization for anyone who wants to research it. We are continuously improving the project. Use it to navigate the topic and choose relevant methods, papers or tools.","feed":"llm-engineering","semantic_path":"llm-engineering:inference-and-quantization","content_type":"reference","version":1,"snapshot_at":"2026-08-04T16:17:00.000Z","publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","card_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901001","permalink_url":"https://mdrss.com/m/901001","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901001/901001.md","file_url":"https://mdrss.com/api/v1/cards/901001/file","raw_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901001/raw","embed_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901001/embed","edit_url":"https://mdrss.com/cards/901001/edit","legacy_url":"https://mdrss.com/s/llm-engineering/awesome-model-quantization-collider-1719a059e8fe"},{"id":2676,"title":"medAlpaca: Finetuned Large Language Models for Medical Question Answering","annotation":"MedAlpaca expands upon both Stanford Alpaca and AlpacaLoRA to offer an advanced suite of large language models specifically fine-tuned for medical question-answering and dialogue applications. Our primary objective is to deliver an array of open-source language models, paving the way for seamless development of medical chatbot solutions.","feed":"llm-engineering","semantic_path":"llm-engineering:evaluation","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:18:22.299Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/evaluation/2676","permalink_url":"https://mdrss.com/m/2676","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/evaluation/2676/2676.md","file_url":"https://mdrss.com/api/v1/cards/2676/file","raw_url":"https://mdrss.com/llm-engineering/evaluation/2676/raw","embed_url":"https://mdrss.com/llm-engineering/evaluation/2676/embed","edit_url":"https://mdrss.com/cards/2676/edit","legacy_url":"https://mdrss.com/s/llm-engineering/kbressem-medalpaca-kbressem-medalpaca-readme"},{"id":2663,"title":"Stable Diffusion web UI","annotation":"A web interface for Stable Diffusion, implemented using Gradio library. Detailed feature showcase with images: Make sure the required dependencies are met and follow the instructions available for: Alternatively, use online services (like Google Colab): 1.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:18:31.127Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2663","permalink_url":"https://mdrss.com/m/2663","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2663/2663.md","file_url":"https://mdrss.com/api/v1/cards/2663/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2663/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2663/embed","edit_url":"https://mdrss.com/cards/2663/edit","legacy_url":"https://mdrss.com/s/llm-engineering/automatic1111-stable-diffusion-webui-automatic1111-stable-diffusion-webui-readme"},{"id":2617,"title":"BS-RoFormer","annotation":"Implementation of Band Split Roformer , SOTA Attention network for music source separation out of ByteDance AI Labs. They beat the previous first place by a large margin.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:31.127Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2617","permalink_url":"https://mdrss.com/m/2617","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2617/2617.md","file_url":"https://mdrss.com/api/v1/cards/2617/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2617/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2617/embed","edit_url":"https://mdrss.com/cards/2617/edit","legacy_url":"https://mdrss.com/s/llm-engineering/lucidrains-bs-roformer-lucidrains-bs-roformer-readme"},{"id":2613,"title":"Soundstorm - Pytorch","annotation":"Implementation of SoundStorm , Efficient Parallel Audio Generation from Google Deepmind, in Pytorch. They basically applied MaskGiT to the residual vector quantized codes from Soundstream .","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:28.561Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2613","permalink_url":"https://mdrss.com/m/2613","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2613/2613.md","file_url":"https://mdrss.com/api/v1/cards/2613/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2613/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2613/embed","edit_url":"https://mdrss.com/cards/2613/edit","legacy_url":"https://mdrss.com/s/llm-engineering/lucidrains-soundstorm-pytorch-lucidrains-soundstorm-pytorch-readme"},{"id":2517,"title":"A Hands-On Guide to Fine-Tuning LLMs with PyTorch and Hugging Face","annotation":"Kindle | Paperback | PDF [Leanpub] | PDF [Gumroad] You can easily load the notebooks directly from GitHub using Colab and run them using a GPU provided by Google. You need to be logged in a Google Account of your own.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:29.841Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2517","permalink_url":"https://mdrss.com/m/2517","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2517/2517.md","file_url":"https://mdrss.com/api/v1/cards/2517/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2517/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2517/embed","edit_url":"https://mdrss.com/cards/2517/edit","legacy_url":"https://mdrss.com/s/llm-engineering/dvgodoy-finetuningllms-dvgodoy-finetuningllms-readme"},{"id":2495,"title":"SimpleTuner","annotation":"SimpleTuner is geared towards simplicity, with a focus on making the code easily understood. This codebase serves as a shared academic exercise, and contributions are welcome.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:18:29.841Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2495","permalink_url":"https://mdrss.com/m/2495","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2495/2495.md","file_url":"https://mdrss.com/api/v1/cards/2495/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2495/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2495/embed","edit_url":"https://mdrss.com/cards/2495/edit","legacy_url":"https://mdrss.com/s/llm-engineering/bghira-simpletuner-bghira-simpletuner-readme"},{"id":2408,"title":"Teaching Data Science","annotation":"Free, open-source Beamer slide decks and code for Machine Learning, Deep Learning, NLP, Generative AI, Maths for ML, and Python, from 1-hour seminars to full courses. Everything here, including slides, code, and notes, has been built by learning from, and citing, the best public material available, and is given back under an open license so anyone can teach, learn, or build on it.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:18:31.127Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2408","permalink_url":"https://mdrss.com/m/2408","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2408/2408.md","file_url":"https://mdrss.com/api/v1/cards/2408/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2408/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2408/embed","edit_url":"https://mdrss.com/cards/2408/edit","legacy_url":"https://mdrss.com/s/llm-engineering/yogeshhk-teachingdatascience-yogeshhk-teachingdatascience-readme"},{"id":2330,"title":"ZodGPT","annotation":"Get structured, fully typed, and validated JSON outputs from OpenAI and Anthropic models. Under the hood, zod-gpt uses functions to coerce the model to always respond as function calls.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:28.561Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2330","permalink_url":"https://mdrss.com/m/2330","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2330/2330.md","file_url":"https://mdrss.com/api/v1/cards/2330/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2330/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2330/embed","edit_url":"https://mdrss.com/cards/2330/edit","legacy_url":"https://mdrss.com/s/llm-engineering/dzhng-zod-gpt-dzhng-zod-gpt-readme"},{"id":2309,"title":"Chat with PDF locally using Ollama + LangChain","annotation":"A powerful local RAG (Retrieval Augmented Generation) application that lets you chat with your PDF documents using Ollama and LangChain. This project includes multiple interfaces: a modern Next.js web app, a Streamlit interface, and Jupyter notebooks for experimentation.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:33.634Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2309","permalink_url":"https://mdrss.com/m/2309","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2309/2309.md","file_url":"https://mdrss.com/api/v1/cards/2309/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2309/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2309/embed","edit_url":"https://mdrss.com/cards/2309/edit","legacy_url":"https://mdrss.com/s/llm-engineering/tonykipkemboi-ollama-pdf-rag-tonykipkemboi-ollama-pdf-rag-readme"},{"id":2269,"title":"Why LoongForge?","annotation":"English | 简体中文 A unified, high-performance framework for training LLMs, VLMs, diffusion, and embodied models. 🌐 Website &nbsp;·&nbsp; 📖 Docs &nbsp;·&nbsp; ✍️ Blog &nbsp;·&nbsp; ⚡ Quick Start &nbsp;·&nbsp; 📊 Performance &nbsp;·&nbsp; 🏛️ Supported Models &nbsp;·&nbsp; 💬 Contact LoongForge is a unified training framework for LLMs, VLMs, diffusion, and embodied models, covering pre-training, continued pre-training, and SFT.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:18:26.106Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2269","permalink_url":"https://mdrss.com/m/2269","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2269/2269.md","file_url":"https://mdrss.com/api/v1/cards/2269/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2269/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2269/embed","edit_url":"https://mdrss.com/cards/2269/edit","legacy_url":"https://mdrss.com/s/llm-engineering/baidu-baige-loongforge-baidu-baige-loongforge-readme"},{"id":2249,"title":"News","annotation":"[&nbsp; Read the Docs &nbsp;] 日本語 | 中文简体 | 中文繁體 --- Code and data for the following works: SWE-bench is a benchmark for evaluating large language models on real world software issues collected from GitHub. Given a codebase and an issue, a language model is tasked with generating a patch that resolves the described problem.","feed":"llm-engineering","semantic_path":"llm-engineering:evaluation","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:22.299Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/evaluation/2249","permalink_url":"https://mdrss.com/m/2249","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/evaluation/2249/2249.md","file_url":"https://mdrss.com/api/v1/cards/2249/file","raw_url":"https://mdrss.com/llm-engineering/evaluation/2249/raw","embed_url":"https://mdrss.com/llm-engineering/evaluation/2249/embed","edit_url":"https://mdrss.com/cards/2249/edit","legacy_url":"https://mdrss.com/s/llm-engineering/princeton-nlp-swe-bench-princeton-nlp-swe-bench-readme"},{"id":2180,"title":"wllama - Wasm binding for llama.cpp","annotation":"For embeddings, please see examples/embeddings/index.html WebGPU support is introduced via PR #215. Upon updating to V3.1, WebGPU will be enabled automatically.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:31.127Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2180","permalink_url":"https://mdrss.com/m/2180","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2180/2180.md","file_url":"https://mdrss.com/api/v1/cards/2180/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2180/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2180/embed","edit_url":"https://mdrss.com/cards/2180/edit","legacy_url":"https://mdrss.com/s/llm-engineering/ngxson-wllama-ngxson-wllama-readme"},{"id":2174,"title":"Aequitas: Bias Auditing & \"Correction\" Toolkit","annotation":"[comment]: <> (Add badges for coverage when we have tests, update repo for other types of badges!) aequitas is an open-source bias auditing and Fair ML toolkit for data scientists, machine learning researchers, and policymakers. We provide an easy-to-use and transparent tool for auditing predictors of ML models, as well as experimenting with \"correcting biased model\" using Fair ML methods in binary classification settings.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:23.611Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2174","permalink_url":"https://mdrss.com/m/2174","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2174/2174.md","file_url":"https://mdrss.com/api/v1/cards/2174/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2174/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2174/embed","edit_url":"https://mdrss.com/cards/2174/edit","legacy_url":"https://mdrss.com/s/llm-engineering/dssg-aequitas-dssg-aequitas-readme"},{"id":2171,"title":"barchart: What is Evidently?","annotation":"Evidently An open-source framework to evaluate, test and monitor ML and LLM-powered systems. Documentation Evidently is an open-source Python library to evaluate, test, and monitor ML and LLM systems—from experiments to production.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:27.387Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2171","permalink_url":"https://mdrss.com/m/2171","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2171/2171.md","file_url":"https://mdrss.com/api/v1/cards/2171/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2171/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2171/embed","edit_url":"https://mdrss.com/cards/2171/edit","legacy_url":"https://mdrss.com/s/llm-engineering/evidentlyai-evidently-evidentlyai-evidently-readme"},{"id":2164,"title":"Lit-LLaMA","annotation":"⚠️ Warning: Not Actively Maintained This repository is no longer actively maintained. For a more up-to-date alternative, please visit the LitGPT project: https://github.com/Lightning-AI/litgpt , which serves as the successor to this repository.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:49.845Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2164","permalink_url":"https://mdrss.com/m/2164","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2164/2164.md","file_url":"https://mdrss.com/api/v1/cards/2164/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2164/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2164/embed","edit_url":"https://mdrss.com/cards/2164/edit","legacy_url":"https://mdrss.com/s/llm-engineering/lightning-ai-lit-llama-lightning-ai-lit-llama-readme"},{"id":2140,"title":"Text Generation Inference","annotation":"A Rust, Python and gRPC server for text generation inference. Used in production at Hugging Face to power Hugging Chat, the Inference API and Inference Endpoints.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:48.518Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2140","permalink_url":"https://mdrss.com/m/2140","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2140/2140.md","file_url":"https://mdrss.com/api/v1/cards/2140/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2140/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2140/embed","edit_url":"https://mdrss.com/cards/2140/edit","legacy_url":"https://mdrss.com/s/llm-engineering/huggingface-text-generation-inference-huggingface-text-generation-inference-read"},{"id":2102,"title":"MuseGAN","annotation":"In a nutshell, we aim to generate polyphonic music of multiple tracks (instruments). The proposed models are able to generate music either from scratch, or by accompanying a track given a priori by the user.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:29.841Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/2102","permalink_url":"https://mdrss.com/m/2102","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/2102/2102.md","file_url":"https://mdrss.com/api/v1/cards/2102/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/2102/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/2102/embed","edit_url":"https://mdrss.com/cards/2102/edit","legacy_url":"https://mdrss.com/s/llm-engineering/salu133445-musegan-salu133445-musegan-readme"},{"id":2075,"title":"rwkv.cpp","annotation":"This is a port of BlinkDL/RWKV-LM to ggerganov/ggml. Besides the usual FP32, it supports FP16, quantized INT4, INT5 and INT8 inference.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:33.634Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2075","permalink_url":"https://mdrss.com/m/2075","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2075/2075.md","file_url":"https://mdrss.com/api/v1/cards/2075/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2075/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/2075/embed","edit_url":"https://mdrss.com/cards/2075/edit","legacy_url":"https://mdrss.com/s/llm-engineering/rwkv-rwkv-cpp-rwkv-rwkv-cpp-readme"},{"id":1965,"title":"Ellora: Enhancing LLMs with LoRA","annotation":"The LLM ecosystem has amazing infrastructure (LoRAX, PEFT, vLLM), but lacks standardized, high-quality capability adapters. Problem: Base models limited to 32K context, need 2M tokens for large repositories Solution: Progressive curriculum learning with vLLM + Unsloth hybrid approach Key Innovation: Hybrid optimization combining vLLM's inference speed with Unsloth's training efficiency - achieving 61x context extension with minimal compute!","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:24.776Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1965","permalink_url":"https://mdrss.com/m/1965","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1965/1965.md","file_url":"https://mdrss.com/api/v1/cards/1965/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1965/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1965/embed","edit_url":"https://mdrss.com/cards/1965/edit","legacy_url":"https://mdrss.com/s/llm-engineering/codelion-ellora-codelion-ellora-readme"},{"id":1963,"title":"LLM Finetuning Toolkit","annotation":"LLM Finetuning toolkit is a config-based CLI tool for launching a series of LLM fine-tuning experiments on your data and gathering their results. From one single yaml config file, control all elements of a typical experimentation pipeline - prompts, open-source LLMs, optimization strategy and LLM testing.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:26.106Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1963","permalink_url":"https://mdrss.com/m/1963","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1963/1963.md","file_url":"https://mdrss.com/api/v1/cards/1963/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1963/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1963/embed","edit_url":"https://mdrss.com/cards/1963/edit","legacy_url":"https://mdrss.com/s/llm-engineering/georgian-io-llm-finetuning-toolkit-georgian-io-llm-finetuning-toolkit-readme"},{"id":1925,"title":"News","annotation":"This is the official repository for ICLR 2025 paper \"Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing\". Magpie generates high-quality alignment data by prompting aligned LLMs with their pre-query templates.","feed":"llm-engineering","semantic_path":"llm-engineering:evaluation","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:22.299Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/evaluation/1925","permalink_url":"https://mdrss.com/m/1925","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/evaluation/1925/1925.md","file_url":"https://mdrss.com/api/v1/cards/1925/file","raw_url":"https://mdrss.com/llm-engineering/evaluation/1925/raw","embed_url":"https://mdrss.com/llm-engineering/evaluation/1925/embed","edit_url":"https://mdrss.com/cards/1925/edit","legacy_url":"https://mdrss.com/s/llm-engineering/magpie-align-magpie-magpie-align-magpie-readme"},{"id":1899,"title":"koboldcpp","annotation":"KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models, inspired by the original KoboldAI. It's a single self-contained distributable that builds off llama.cpp and adds many additional powerful features.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:18:48.518Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1899","permalink_url":"https://mdrss.com/m/1899","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1899/1899.md","file_url":"https://mdrss.com/api/v1/cards/1899/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1899/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1899/embed","edit_url":"https://mdrss.com/cards/1899/edit","legacy_url":"https://mdrss.com/s/llm-engineering/lostruins-koboldcpp-lostruins-koboldcpp-readme"},{"id":1891,"title":"DLLM RL","annotation":"We also introduce a diffusion-based value model that reduces variance and improves stability during optimization. Based on TraceRL, we derive a series of diffusion language models, TraDo, which achieve state-of-the-art performance on math and coding reasoning tasks.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:33.634Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1891","permalink_url":"https://mdrss.com/m/1891","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1891/1891.md","file_url":"https://mdrss.com/api/v1/cards/1891/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1891/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1891/embed","edit_url":"https://mdrss.com/cards/1891/edit","legacy_url":"https://mdrss.com/s/llm-engineering/gen-verse-dllm-rl-gen-verse-dllm-rl-readme"},{"id":1821,"title":"RouteLLM","annotation":"RouteLLM is a framework for serving and evaluating LLM routers. [Blog ] [Paper ] Our core features include: From PyPI From source Let's walkthrough replacing an existing OpenAI client to route queries between LLMs instead of using only a single model.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:24.776Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1821","permalink_url":"https://mdrss.com/m/1821","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1821/1821.md","file_url":"https://mdrss.com/api/v1/cards/1821/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1821/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1821/embed","edit_url":"https://mdrss.com/cards/1821/edit","legacy_url":"https://mdrss.com/s/llm-engineering/lm-sys-routellm-lm-sys-routellm-readme"},{"id":1774,"title":"Key Features","annotation":"MASFactory is a graph-centric framework for orchestrating Multi-Agent Systems with Vibe Graphing: Start from intent, generate a graph design, preview and refine it in a visual environment, compile it into an executable workflow, and trace node states, messages, and shared state at runtime. Turn natural-language intent into a structural design, then iteratively converge to an executable, reusable workflow.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:23.611Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1774","permalink_url":"https://mdrss.com/m/1774","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1774/1774.md","file_url":"https://mdrss.com/api/v1/cards/1774/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1774/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1774/embed","edit_url":"https://mdrss.com/cards/1774/edit","legacy_url":"https://mdrss.com/s/llm-engineering/bupt-gamma-masfactory-bupt-gamma-masfactory-readme"},{"id":1740,"title":"XTuring","annotation":"Fine‑tune, evaluate, and run private, personalized LLMs xTuring makes it simple, fast, and cost‑efficient to fine‑tune open‑source LLMs (e.g., GPT‑OSS, LLaMA/LLaMA 2, Qwen3, MiniMax M2, GPT‑J, GPT‑2, DistilGPT‑2, Mamba) on your own data — locally or in your private cloud. Why xTuring: Run a small, CPU‑friendly example first: Want bigger models and reasoning controls?","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:23.611Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1740","permalink_url":"https://mdrss.com/m/1740","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1740/1740.md","file_url":"https://mdrss.com/api/v1/cards/1740/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1740/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1740/embed","edit_url":"https://mdrss.com/cards/1740/edit","legacy_url":"https://mdrss.com/s/llm-engineering/stochasticai-xturing-stochasticai-xturing-readme"},{"id":1726,"title":"REST API examples","annotation":"I've started to work on reimplementation of the library here: FastTensors Please star it if you'd like to see GGML-compatible implementation in pure Go. Please check out my related project Booster We dream of a world where fellow ML hackers are grokking REALLY BIG GPT models in their homelabs without having GPU clusters consuming a shit tons of $$$.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:33.634Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1726","permalink_url":"https://mdrss.com/m/1726","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1726/1726.md","file_url":"https://mdrss.com/api/v1/cards/1726/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1726/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1726/embed","edit_url":"https://mdrss.com/cards/1726/edit","legacy_url":"https://mdrss.com/s/llm-engineering/gotzmann-llama-go-gotzmann-llama-go-readme"},{"id":1671,"title":"QLoRA: Efficient Finetuning of Quantized LLMs","annotation":"This repo supports the paper \"QLoRA: Efficient Finetuning of Quantized LLMs\", an effort to democratize access to LLM research. QLoRA uses bitsandbytes for quantization and is integrated with Hugging Face's PEFT and transformers libraries.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:33.634Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1671","permalink_url":"https://mdrss.com/m/1671","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1671/1671.md","file_url":"https://mdrss.com/api/v1/cards/1671/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1671/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1671/embed","edit_url":"https://mdrss.com/cards/1671/edit","legacy_url":"https://mdrss.com/s/llm-engineering/artidoro-qlora-artidoro-qlora-readme"},{"id":1663,"title":"What is NannyML?","annotation":"Website • Docs • Community Slack NannyML is an open-source python library that allows you to estimate post-deployment model performance (without access to targets), detect data drift, and intelligently link data drift alerts back to changes in model performance. Built for data scientists, NannyML has an easy-to-use interface, interactive visualizations, is completely model-agnostic and currently supports all tabular use cases, classification and regression.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:27.387Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1663","permalink_url":"https://mdrss.com/m/1663","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1663/1663.md","file_url":"https://mdrss.com/api/v1/cards/1663/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1663/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1663/embed","edit_url":"https://mdrss.com/cards/1663/edit","legacy_url":"https://mdrss.com/s/llm-engineering/nannyml-nannyml-nannyml-nannyml-readme"},{"id":1653,"title":"What is RAGFlow?","annotation":"Cloud | Documentation | Roadmap | Discord 📕 Table of Contents RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs. It offers a streamlined RAG workflow adaptable to enterprises of any scale.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:29.841Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1653","permalink_url":"https://mdrss.com/m/1653","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1653/1653.md","file_url":"https://mdrss.com/api/v1/cards/1653/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1653/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1653/embed","edit_url":"https://mdrss.com/cards/1653/edit","legacy_url":"https://mdrss.com/s/llm-engineering/infiniflow-ragflow-infiniflow-ragflow-readme"},{"id":1626,"title":"GeoCalib is an algorithm for single-image calibration: it estimates the camera intrinsics and gravity direction from a single image only","annotation":"GeoCalib is an algorithm for single-image calibration: it estimates the camera intrinsics and gravity direction from a single image only. By combining geometric optimization with deep learning, GeoCalib provides a more flexible and accurate calibration compared to previous approaches.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:22.299Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1626","permalink_url":"https://mdrss.com/m/1626","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1626/1626.md","file_url":"https://mdrss.com/api/v1/cards/1626/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1626/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1626/embed","edit_url":"https://mdrss.com/cards/1626/edit","legacy_url":"https://mdrss.com/s/llm-engineering/cvg-geocalib-cvg-geocalib-readme"},{"id":1608,"title":"About UltraRAG","annotation":"Designed for research exploration and industrial prototyping, UltraRAG standardizes core RAG components (Retriever, Generation, etc.) as independent MCP Servers, combined with the powerful workflow orchestration capabilities of the MCP Client. Developers can achieve precise orchestration of complex control structures such as conditional branches and loops simply through YAML configuration.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:29.841Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1608","permalink_url":"https://mdrss.com/m/1608","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1608/1608.md","file_url":"https://mdrss.com/api/v1/cards/1608/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1608/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1608/embed","edit_url":"https://mdrss.com/cards/1608/edit","legacy_url":"https://mdrss.com/s/llm-engineering/openbmb-ultrarag-openbmb-ultrarag-readme"},{"id":1593,"title":"AutoRAG","annotation":"A self-evolving librarian agent for document collections. AutoRAG searches your PDFs, wikis, notes, research papers, and knowledge bases — then curates the results into clean, numbered knowledge units.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:32.550Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1593","permalink_url":"https://mdrss.com/m/1593","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1593/1593.md","file_url":"https://mdrss.com/api/v1/cards/1593/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1593/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1593/embed","edit_url":"https://mdrss.com/cards/1593/edit","legacy_url":"https://mdrss.com/s/llm-engineering/marker-inc-korea-autorag-marker-inc-korea-autorag-readme"},{"id":1583,"title":"A Quick Overview","annotation":"MedSegDiff is a Diffusion Probabilistic Model (DPM) based framework for the Segmentation and Reconstruction of organs/tissues from the medical images. The algorithm is elaborated on our paper MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model MedSegDiff-V2: Diffusion based Medical Image Segmentation with Transformer.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:26.106Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1583","permalink_url":"https://mdrss.com/m/1583","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1583/1583.md","file_url":"https://mdrss.com/api/v1/cards/1583/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1583/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1583/embed","edit_url":"https://mdrss.com/cards/1583/edit","legacy_url":"https://mdrss.com/s/llm-engineering/imprintlab-medsegdiff-imprintlab-medsegdiff-readme"},{"id":1557,"title":"Demo","annotation":"A self-contained image bundles the tool + the Claude Code and Codex CLIs. You log in once and the sessions persist in named volumes — no re-login on later runs.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:23.611Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1557","permalink_url":"https://mdrss.com/m/1557","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1557/1557.md","file_url":"https://mdrss.com/api/v1/cards/1557/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1557/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1557/embed","edit_url":"https://mdrss.com/cards/1557/edit","legacy_url":"https://mdrss.com/s/llm-engineering/greydgl-pentestgpt-greydgl-pentestgpt-readme"},{"id":1511,"title":"LLM Zoo: democratizing ChatGPT","annotation":"⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡ [[Tech Report]](assets/llmzoo.pdf) technology gifted by the creator. For example, many pioneers have made great efforts to spread the use of light bulbs and vaccines to developing countries.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:48.518Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1511","permalink_url":"https://mdrss.com/m/1511","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1511/1511.md","file_url":"https://mdrss.com/api/v1/cards/1511/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1511/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1511/embed","edit_url":"https://mdrss.com/cards/1511/edit","legacy_url":"https://mdrss.com/s/llm-engineering/freedomintelligence-llmzoo-freedomintelligence-llmzoo-readme"},{"id":1484,"title":"TrainTrain","annotation":"2025.12.09 Support Z-Image Turbo Standalone training is now supported. For details, please refer to the Standalone Environment Setup Repository.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:18:23.611Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1484","permalink_url":"https://mdrss.com/m/1484","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1484/1484.md","file_url":"https://mdrss.com/api/v1/cards/1484/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1484/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1484/embed","edit_url":"https://mdrss.com/cards/1484/edit","legacy_url":"https://mdrss.com/s/llm-engineering/hako-mikan-sd-webui-traintrain-hako-mikan-sd-webui-traintrain-readme"},{"id":1483,"title":"MLX-LM-LORA","annotation":"With MLX-LM-LoRA you can, train Large Language Models locally on Apple Silicon using MLX. Training works with all models supported by MLX-LM, including: Training Types: Training Algorithms: Quantization Aware Training (QAT): Training Your Custom Preference Model: --- The main command is mlxlmlora.train.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:26.106Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1483","permalink_url":"https://mdrss.com/m/1483","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1483/1483.md","file_url":"https://mdrss.com/api/v1/cards/1483/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1483/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1483/embed","edit_url":"https://mdrss.com/cards/1483/edit","legacy_url":"https://mdrss.com/s/llm-engineering/goekdeniz-guelmez-mlx-lm-lora-goekdeniz-guelmez-mlx-lm-lora-readme"},{"id":1425,"title":"What you'll learn","annotation":"LLM Twin Course: Building Your Production-Ready AI Replica Learn to architect and implement a production-ready LLM & RAG system by building your LLM Twin From data gathering to productionizing LLMs using LLMOps good practices. by Decoding AI By finishing the \"LLM Twin: Building Your Production-Ready AI Replica\" free course, you will learn how to design, train, and deploy a production-ready LLM twin of yourself powered by LLMs, vector DBs, and LLMOps good practices.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:18:48.518Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1425","permalink_url":"https://mdrss.com/m/1425","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1425/1425.md","file_url":"https://mdrss.com/api/v1/cards/1425/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1425/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1425/embed","edit_url":"https://mdrss.com/cards/1425/edit","legacy_url":"https://mdrss.com/s/llm-engineering/decodingai-magazine-llm-twin-course-decodingai-magazine-llm-twin-course-readme"},{"id":1383,"title":"Comparison with FAISS","annotation":"USearch and FAISS both employ the same HNSW algorithm, but they differ significantly in their design principles. USearch is compact and broadly compatible without sacrificing performance, primarily focusing on user-defined metrics and fewer dependencies.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:32.550Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1383","permalink_url":"https://mdrss.com/m/1383","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1383/1383.md","file_url":"https://mdrss.com/api/v1/cards/1383/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1383/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1383/embed","edit_url":"https://mdrss.com/cards/1383/edit","legacy_url":"https://mdrss.com/s/llm-engineering/unum-cloud-usearch-unum-cloud-usearch-readme"},{"id":1381,"title":"Deep Learning Roadmap","annotation":"figure:: img/mainpage/subscribe.gif :target: https://machinelearningmindset.com/subscription/ Slack Group .. image:: https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat :target: https://github.com/astorfi/Deep-Learning-World/pulls ..","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:28.561Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1381","permalink_url":"https://mdrss.com/m/1381","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1381/1381.md","file_url":"https://mdrss.com/api/v1/cards/1381/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1381/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1381/embed","edit_url":"https://mdrss.com/cards/1381/edit","legacy_url":"https://mdrss.com/s/llm-engineering/astorfi-deep-learning-roadmap-astorfi-deep-learning-roadmap-readme"},{"id":1358,"title":"Kronk","annotation":"Copyright 2025-2026 Ardan Labs hello@ardanlabs.com https://kronkai.com This project lets you use Go for hardware accelerated local inference with llama.cpp and whisper.cpp directly integrated into your Go applications via the yzma and bucky modules. Kronk provides a high-level API that feels similar to using an OpenAI compatible API.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:27.387Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1358","permalink_url":"https://mdrss.com/m/1358","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1358/1358.md","file_url":"https://mdrss.com/api/v1/cards/1358/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1358/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1358/embed","edit_url":"https://mdrss.com/cards/1358/edit","legacy_url":"https://mdrss.com/s/llm-engineering/ardanlabs-kronk-ardanlabs-kronk-readme"},{"id":1347,"title":"Augustus - LLM Vulnerability Scanner","annotation":"Augustus is a Go-based LLM vulnerability scanner for security professionals. It tests large language models against a wide range of adversarial attacks, integrates with 28 LLM providers, and produces actionable vulnerability reports.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:28.561Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1347","permalink_url":"https://mdrss.com/m/1347","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1347/1347.md","file_url":"https://mdrss.com/api/v1/cards/1347/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1347/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1347/embed","edit_url":"https://mdrss.com/cards/1347/edit","legacy_url":"https://mdrss.com/s/llm-engineering/praetorian-inc-augustus-praetorian-inc-augustus-readme"},{"id":1310,"title":"Deep Learning Roadmap","annotation":"image:: https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat :target: https://github.com/osforscience/deep-learning-all-you-need/pulls .. image:: https://badges.frapsoft.com/os/v2/open-source.png?v=103 :target: https://github.com/ellerbrock/open-source-badge/ ..","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:28.561Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1310","permalink_url":"https://mdrss.com/m/1310","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1310/1310.md","file_url":"https://mdrss.com/api/v1/cards/1310/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1310/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1310/embed","edit_url":"https://mdrss.com/cards/1310/edit","legacy_url":"https://mdrss.com/s/llm-engineering/instillai-deep-learning-roadmap-instillai-deep-learning-roadmap-readme"},{"id":1291,"title":"A Toolkit for Document-level Event Extraction with & without Triggers","annotation":"This project aims at building a universal toolkit for extracting events automatically from documents 📄 (long texts). The details can be found in our paper: Tong Zhu, Xiaoye Qu, Wenliang Chen, Zhefeng Wang, Baoxing Huai, Nicholas Yuan, Min Zhang.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:27.387Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1291","permalink_url":"https://mdrss.com/m/1291","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1291/1291.md","file_url":"https://mdrss.com/api/v1/cards/1291/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1291/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1291/embed","edit_url":"https://mdrss.com/cards/1291/edit","legacy_url":"https://mdrss.com/s/llm-engineering/spico197-docee-spico197-docee-readme"},{"id":1286,"title":"ControlNet for Stable Diffusion WebUI","annotation":"The WebUI extension for ControlNet and other injection-based SD controls. This extension is for AUTOMATIC1111's Stable Diffusion web UI, allows the Web UI to add ControlNet to the original Stable Diffusion model to generate images.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:18:27.387Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1286","permalink_url":"https://mdrss.com/m/1286","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1286/1286.md","file_url":"https://mdrss.com/api/v1/cards/1286/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1286/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1286/embed","edit_url":"https://mdrss.com/cards/1286/edit","legacy_url":"https://mdrss.com/s/llm-engineering/mikubill-sd-webui-controlnet-mikubill-sd-webui-controlnet-readme"},{"id":1284,"title":"Deep Learning for Mathematical Reasoning (DL4MATH)","annotation":"This repository is the reading list on Deep Learning for Mathematical Reasoning (DL4MATH). Contributors: Pan Lu @UCLA, Liang Qiu @UCLA, Wenhao Yu @Notre Dame, Sean Welleck @UW, Kai-Wei Chang @UCLA For more details, please refer to the paper: A Survey of Deep Learning for Mathematical Reasoning.","feed":"llm-engineering","semantic_path":"llm-engineering:evaluation","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:18:08.058Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/evaluation/1284","permalink_url":"https://mdrss.com/m/1284","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/evaluation/1284/1284.md","file_url":"https://mdrss.com/api/v1/cards/1284/file","raw_url":"https://mdrss.com/llm-engineering/evaluation/1284/raw","embed_url":"https://mdrss.com/llm-engineering/evaluation/1284/embed","edit_url":"https://mdrss.com/cards/1284/edit","legacy_url":"https://mdrss.com/s/llm-engineering/lupantech-dl4math-lupantech-dl4math-readme"},{"id":1280,"title":"Evalscope","annotation":"中文 &nbsp ｜ &nbsp English &nbsp 📖 中文文档 &nbsp ｜ &nbsp 📖 English Documentation EvalScope is a one-stop LLM evaluation framework built by the ModelScope Community. Just one command to start — it supports model capability evaluation, inference performance stress testing, and result visualization.","feed":"llm-engineering","semantic_path":"llm-engineering:serving-and-retrieval","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:18:33.634Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1280","permalink_url":"https://mdrss.com/m/1280","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1280/1280.md","file_url":"https://mdrss.com/api/v1/cards/1280/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1280/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1280/embed","edit_url":"https://mdrss.com/cards/1280/edit","legacy_url":"https://mdrss.com/s/llm-engineering/modelscope-evalscope-modelscope-evalscope-readme"},{"id":1276,"title":"AI Audio Datasets (AI-ADS)","annotation":"AI Audio Datasets (AI-ADS) 🎵, including Speech, Music, and Sound Effects, which can provide training data for Generative AI, AIGC, AI model training, intelligent audio tool development, and audio applications.","feed":"llm-engineering","semantic_path":"llm-engineering:models-and-training","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:18:24.776Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/llm-engineering/models-and-training/1276","permalink_url":"https://mdrss.com/m/1276","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/models-and-training/1276/1276.md","file_url":"https://mdrss.com/api/v1/cards/1276/file","raw_url":"https://mdrss.com/llm-engineering/models-and-training/1276/raw","embed_url":"https://mdrss.com/llm-engineering/models-and-training/1276/embed","edit_url":"https://mdrss.com/cards/1276/edit","legacy_url":"https://mdrss.com/s/llm-engineering/yuan-manx-ai-audio-datasets-yuan-manx-ai-audio-datasets-readme"}]}