firecrawl/ai-research-skills
59 skills · 342 total installs
$npx skills add firecrawl/ai-research-skillsSkillInstalls
llama-cppRuns LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware.chromaOpen-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata.sglangFast structured generation and serving for LLMs with RadixAttention prefix caching.unslothExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimizationhuggingface-tokenizersFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms.langchainllamaindexData framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying.prompt-guardMeta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU).ray-trainDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes.sentencepieceLanguage-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms.tensorrt-llmOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency.axolotlExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal supportconstitutional-aiAnthropic's method for training harmless AI through self-improvement.deepspeedExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attentiongptqPost-training 4-bit quantization for LLMs with minimal accuracy loss.grpo-rl-trainingExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model trainingllama-factoryExpert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal supportllamaguardMeta's 7-8B specialized moderation model for LLM input/output filtering.mlflowTrack ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML…nanogptEducational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy.nemo-curatorGPU-accelerated data curation for LLM training. Supports text/image/video/audio.nemo-guardrailsNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII…pytorch-fsdp2Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing.pytorch-lightningHigh-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate.ray-dataScalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images.tensorboardVisualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML…weights-and-biasesTrack ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B -…accelerateautogptawqActivation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss.bigcode-evaluation-harnessEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics.bitsandbytesQuantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss.crewaiflash-attentionOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction.ggufGGUF format and llama.cpp quantization for efficient CPU/GPU inference.hqqHalf-Quadratic Quantization for LLMs without calibration data.lambda-labsReserved and on-demand GPU cloud instances for ML training and inference.litgptImplements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral).lm-evaluation-harnessEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag).mambaState-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache.megatron-coremilesProvides guidance for enterprise-grade RL training using miles, a production-ready fork of slime.modalServerless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs,…nemo-evaluatorEvaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.nnsightProvides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.openrlhfHigh-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3.peftParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.pyveneProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework.rwkvRNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential).saelensProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features.simpoSimple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0).skypilotMulti-cloud orchestration for ML workloads with automatic cost optimization.slimeProvides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework.torchforgeProvides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms.torchtitanProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).transformer-lensProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation…trl-fine-tuningFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward…verlProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL).vllmServes LLMs with high throughput using vLLM's PagedAttention and continuous batching.