lambda-labs-gpu-cloud
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
huggingface-tokenizers
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
nemo-curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
obliteratus
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.
clip
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
segment-anything-model
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
grpo-rl-training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
peft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
pytorch-fsdp
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
simpo-training
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
slime-rl-training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
bug-hunter
分布式多智能体缺陷检测总控技能。基于输入随机化、角色化并行评审、语义桶化、加权共识与裁决复核输出高信噪比代码评审报告。用于大规模 PR、复杂逻辑变更、安全敏感改动或单智能体评审召回率不足的场景。
bug-hunter-stage2-parallel-review
bug-hunter 阶段 2 技能。负责将随机化后的 diff 按 persona 矩阵分发给 8 个子智能体并行评审，并收集统一 JSON 结果。
bug-hunter-stage3-evidence-fusion
bug-hunter 阶段 3 技能。负责对多智能体原始发现做语义去重、桶化聚类与冲突识别，形成可投票的缺陷候选池。
bug-hunter-stage4-consensus-judge
bug-hunter 阶段 4 技能。负责对缺陷桶执行加权共识投票，筛选过阈值问题，并输出裁决级结构化评审报告。
generate-release-notes
Generate release notes for the new NNCF release.
numerai-experiment-design
Design and manage Numerai experiments in this repo for any model idea.
numerai-model-implementation
Add a new Numerai model type to the agents training pipeline. Use when you need to register a model in `agents/code/modeling/utils/model_factory.py`, handle fit/predict quirks in `agents/code/modeling/utils/numerai_cv.py`, and update configs so the model can run via `python -m agents.code.modeling`.