firecrawl/ai-research-skills

1

llama-cpp Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M…

firecrawl/ai-research-skills

32

2

audiocraft-audio-generation PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you ne…

firecrawl/ai-research-skills

28

3

knowledge-distillation Compress large language models using knowledge distillation from teacher to student models. Use when deploying smalle…

firecrawl/ai-research-skills

28

4

speculative-decoding Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use wh…

firecrawl/ai-research-skills

28

5

llamaindex Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing,…

firecrawl/ai-research-skills

27

6

stable-diffusion-image-generation State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating…

firecrawl/ai-research-skills

27

7

unsloth Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

firecrawl/ai-research-skills

27

8

sentence-transformers Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic s…

firecrawl/ai-research-skills

26

9

whisper OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and …

firecrawl/ai-research-skills

26

10

chroma Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text searc…

firecrawl/ai-research-skills

25

11

dspy Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and…

firecrawl/ai-research-skills

25

12

evaluating-llms-harness Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking …

firecrawl/ai-research-skills

25

13

long-context Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when…

firecrawl/ai-research-skills

25

14

ml-paper-writing Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research…

firecrawl/ai-research-skills

25

15

serving-llms-vllm Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production L…

firecrawl/ai-research-skills

25

16

sglang Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, const…

firecrawl/ai-research-skills

25

17

crewai-multi-agent Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents wo…

firecrawl/ai-research-skills

24

18

segment-anything-model Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images us…

firecrawl/ai-research-skills

24

19

tensorboard Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile pe…

firecrawl/ai-research-skills

24

20

torchforge-rl-training Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Us…

firecrawl/ai-research-skills

24

21

transformer-lens-interpretability Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transform…

firecrawl/ai-research-skills

24

22

awq-quantization Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when de…

firecrawl/ai-research-skills

23

23

blip-2-vision-language Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, v…

firecrawl/ai-research-skills

23

24

clip OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross…

firecrawl/ai-research-skills

23

25

evaluating-code-models Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when …

firecrawl/ai-research-skills

23

26

fine-tuning-with-trl Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/…

firecrawl/ai-research-skills

23

27

guidance Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and…

firecrawl/ai-research-skills

23

28

hqq-quantization Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision with…

firecrawl/ai-research-skills

23

29

huggingface-tokenizers Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Suppor…

firecrawl/ai-research-skills

23

30

langchain Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, An…

firecrawl/ai-research-skills

23

31

langsmith-observability LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating m…

firecrawl/ai-research-skills

23

32

llava Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP v…

firecrawl/ai-research-skills

23

33

modal-serverless-gpu Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure…

firecrawl/ai-research-skills

23

34

model-merging Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating special…

firecrawl/ai-research-skills

23

35

nemo-curator GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× fa…

firecrawl/ai-research-skills

23

36

optimizing-attention-flash Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/…

firecrawl/ai-research-skills

23

37

outlines Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local m…

firecrawl/ai-research-skills

23

38

pinecone Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + spar…

firecrawl/ai-research-skills

23

39

prompt-guard Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+…

firecrawl/ai-research-skills

23

40

pyvene-interventions Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention frame…

firecrawl/ai-research-skills

23

41

ray-train Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nod…

firecrawl/ai-research-skills

23

42

sentencepiece Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences…

firecrawl/ai-research-skills

23

43

tensorrt-llm Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment…

firecrawl/ai-research-skills

23

44

autogpt-agents Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, …

firecrawl/ai-research-skills

22

45

axolotl Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimo…

firecrawl/ai-research-skills

22

46

constitutional-ai Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with s…

firecrawl/ai-research-skills

22

47

deepspeed Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/F…

firecrawl/ai-research-skills

22

48

distributed-llm-pretraining-torchtitan Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use whe…

firecrawl/ai-research-skills

22

49

faiss Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU…

firecrawl/ai-research-skills

22

50

gguf-quantization GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardwar…

firecrawl/ai-research-skills

22