AI Dataset2023
Contains short, small-vocabulary stories synthetically generated by GPT-3.5 and GPT-4 for training and evaluating compact language models. Includes multiple splits, a GPT-4-only V2 subset, and archive files with prompts and metadata for reproducible experiments.
AI Model2023
Pretrained multilingual speech encoder for ASR and related speech tasks (300M parameters), trained with wav2vec2-style self-supervision on ~500k hours across 1,400+ languages. Designed for 16 kHz audio and typically fine-tuned for downstream ASR/translation/classification.
AI Model2023
Multilingual automatic speech recognition and speech-translation model that transcribes and translates audio. Trained on a mix of weakly labeled and pseudo-labeled data (1M + 4M hours), uses 128 Mel bins and adds a Cantonese token, and supports timestamps and long-form chunking for offline ASR and translation.
AI Deploy2024
Applies quantization, pruning, distillation, speculative decoding and sparsity to compress and accelerate deep learning models, producing exportable checkpoints ready for deployment on TensorRT‑LLM, TensorRT, vLLM and similar inference runtimes.
AI Dataset2024
Provides ~1.3 trillion tokens of web pages filtered for educational quality using an LLM-trained classifier; includes per-Crawl configs, smaller random samples (10B/100B/350B tokens), and the classifier code and model for reproducible filtering.
AI Model2024
Provides code, pretrained weights, and tooling for protein language models and structure prediction — including ESMC, ESMFold2, sparse autoencoders (SAEs), and the ESM Atlas. Includes model checkpoints, tutorials, Hugging Face & Biohub integration, and an MIT license.
AI Model2024
An instruction-tuned 8B Llama 3.1 model for multilingual conversational text generation, built for assistant-style chat and long-context inputs (up to 128k tokens). Available for use via the Transformers pipeline and inference endpoints, with common optimizations like safetensors.
AI Dataset2024
Provides pre-parsed Parquet snapshots of English and French Wikipedia articles with structured fields (sections, infoboxes, tables, references, images) and credibility signals — optimized for large-scale analysis, retrieval-augmented generation, and model development.
Embodied AI2024
Provides an open platform of omnimodal world models, datasets, and tools to build Physical AI — joint perception, generation, and action reasoning for robots, autonomous vehicles, and smart infrastructure. Supports images, video, audio, and action-conditioned workflows.
Provides end-to-end PyTorch scripts to download/prepare data, implement a transformer from scratch, train LLMs (13M→billion-scale) and generate text. Emphasizes educational clarity and single‑GPU experiments; useful for researchers or hobbyists, but large-scale training still requires substantial compute and engineering.
A concise textbook-style book that explains foundational concepts and techniques for large language models, covering pre-training, generative models, prompting, alignment, inference, and reasoning. Structured as self-contained chapters for readers with some ML/NLP background or those seeking a principled introduction to LLM foundations.
AI Dataset2025
High-quality, efficiently verified and filtered web corpus for LLM pretraining — supplies ~1 trillion English tokens and ~120 billion Chinese tokens with English/Chinese Parquet splits. Designed for large-scale pretraining experiments and data-filtering research.