AI Deploy2021
Serves predictive and generative ML models on Kubernetes via a single InferenceService CRD, with scale-to-zero, canary rollouts, and an OpenAI-compatible LLM path on vLLM. One autoscaling abstraction over PyTorch, XGBoost, ONNX, and HuggingFace.
AI Dataset2022
A 57-subject multiple-choice benchmark for measuring broad language understanding in LLMs; provides per-subject configs and test/dev/auxiliary_train splits for few-/zero-shot evaluation, widely used for model comparison and academic reporting.
AI Dataset2022
Provides 115M public GitHub source files (≈873GB of code, ~1TB uncompressed) with per-file metadata (repo, path, language, license). Supports streaming, language/license filtering and full download for training and evaluating code LLMs and code generation models.
AI Dataset2022
Provides cleaned, per-language snapshots of Wikipedia articles (id, url, title, text) packaged as Hugging Face dataset configs (Parquet). Covers 300+ language configs and dated dumps — useful for language modeling, multilingual NLP, retrieval, and RAG pipelines.
AI Dataset2022
Benchmark dataset of ~8.5k grade-school math word problems with step-by-step solutions and calculator annotations for evaluating multi-step arithmetic reasoning in language models. Provided in two configs (main and socratic) and commonly used for chain-of-thought prompting, fine-tuning, and verifier training.
AI Dataset2022
Canonical ILSVRC ImageNet-1k for 1,000-way image classification — provides roughly 1.2M labeled images (train/val/test) packaged as optimized Parquet for easy loading with Hugging Face Datasets, Dask, and Polars. Verify licensing and distribution constraints before use.
AI Infra2022
Fused CUDA kernels that compute exact attention without ever writing the full N×N score matrix to GPU memory, cutting memory from quadratic to linear and speeding up training and inference on A100/H100. Ships FlashAttention-2/3 plus KV-cache decode paths.
AI Model2022
Runs pretrained diffusion models for image, video, and audio generation through composable pipelines. It separates pipelines, schedulers, models, adapters, and memory optimizations so teams can prototype quickly without locking into one model family.
AI Model2022
Rust-and-Python toolkit that serves open-source LLMs (Llama, Falcon, Mixtral, StarCoder) over HTTP/gRPC with tensor parallelism, continuous batching, Flash/Paged Attention and quantization. Now in maintenance mode, pointing users toward vLLM and SGLang.
AI Audio2022
Alibaba DAMO Academy, Northwestern Polytechnical University (NWPU) +5Alibaba DAMO Academy, ModelScope
Bundles ASR, voice activity detection, punctuation, and speaker diarization into one pipeline, with pretrained models like Paraformer and SenseVoice. SenseVoice runs ~17x realtime on CPU; also ships streaming ASR and an OpenAI-compatible API.
Chatbot2022
Curated, community-maintained collection of ready-to-use prompts — roles like interviewer, translator, and code reviewer — that copy directly into ChatGPT, Claude, Gemini, or local models. Available as CSV, markdown, and a Hugging Face dataset.
AI Dataset2022
Provides human preference comparison pairs and red-team conversation transcripts collected by Anthropic for training preference/reward models and studying harmful model behaviors; intended for RLHF and safety research, not for supervised fine-tuning of dialogue agents.