AI-research-SKILLs

Skills (92)

• autoresearch

  v1.0.0MIT412 lines3571 words7 blocks

  Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear opti...

  json
• example-skill-name

  v1.0.0MIT107 lines275 words6 blocks

  Brief third-person description of what this skill does and when to use it. Include key terms and triggers for discovery. Maximum 1024 characters.

  bash
• sentencepiece

  v1.0.0MIT236 lines636 words10 blocks

  Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), ...

  bashpython
• huggingface-tokenizers

  v1.0.0MIT517 lines1561 words17 blocks

  Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram al...

  bashpython
• pinecone

  v1.0.0MIT359 lines888 words12 blocks

  Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and name...

  bashpython
• chroma

  v1.0.0MIT407 lines970 words17 blocks

  Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-f...

  bashpython
• sentence-transformers

  v1.0.0MIT256 lines712 words11 blocks

  Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrie...

  bashpython
• faiss

  v1.0.0MIT222 lines677 words10 blocks

  Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index ...

  bashpython
• qdrant-vector-search

  v1.0.0MIT494 lines1271 words19 blocks

  High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor...

  bashpython
• huggingface-accelerate

  v1.0.0MIT333 lines875 words19 blocks

  Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic de...

  bashjsonpython
• ray-train

  v1.0.0MIT407 lines1104 words14 blocks

  Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tunin...

  bashpython
• deepspeed

  v1.0.0MIT142 lines19436 words9 blocks

  Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

  python
• training-llms-megatron

  v1.0.0MIT367 lines1262 words22 blocks

  Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parame...

  bash
• pytorch-fsdp2

  v1.0.0MIT232 lines1295 words

  Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use w...

• pytorch-lightning

  v1.0.0MIT347 lines958 words13 blocks

  High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scale...

  bashpython
• audiocraft-audio-generation

  v1.0.0MIT565 lines1560 words18 blocks

  PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text de...

  bashpython
• stable-diffusion-image-generation

  v1.0.0MIT520 lines1380 words25 blocks

  State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, perfor...

  bashpython
• clip

  v1.0.0MIT254 lines779 words8 blocks

  OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M...

  bashpython
• llava

  v1.0.0MIT305 lines937 words15 blocks

  Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA l...

  bashpython
• fine-tuning-openvla-oft

  v1.0.0MIT442 lines1790 words24 blocks

  Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM con...

  bashpythontext