AI Model2022
Pretrained uncased English BERT base model for masked language modeling and next-sentence prediction. ~110M parameters, pretrained on BookCorpus and English Wikipedia; commonly fine-tuned for classification, token labeling, and question answering.
AI Model2022
Encodes sentences and short paragraphs into 384-dimensional semantic vectors for retrieval, clustering, and similarity tasks. Fine-tuned from MiniLM-L6-H384 on ~1.17B sentence pairs with a contrastive objective; defaults to 256 word-piece truncation.
AI Model2022
Autoregressive transformer that generates English text from a prompt and can be fine-tuned for downstream NLP tasks. This is the 124M-parameter GPT-2 checkpoint (causal LM, byte-level BPE, 1024-token context) hosted on Hugging Face.
AI Model2022
A compact pretrained bidirectional Transformer distilled from BERT base for masked language modeling and downstream NLP fine-tuning. Trained via knowledge distillation on BookCorpus and English Wikipedia, it reduces size/latency (≈67M params) while preserving BERT-like representations.
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 Train2025
A PyTorch DTensor-native SPMD library for training and fine-tuning LLMs, VLMs, diffusion and retrieval models. Integrates with Hugging Face for day-0 model support, provides YAML-driven recipes, DTensor/FSDP2 parallelism and NVIDIA-optimized kernels (Transformer Engine, DeepEP, FlexAttn).
AI Image2025
Provides versioned LoRA weights and ComfyUI workflows to perform face, head, and full-person swaps for Qwen Image, Qwen Image Edit, Flux 2 Klein and Krea 2; includes multiple swap levels, input-order conventions, and recommended base-model pairings—start at LoRA strength 1.0 and adjust.
AI Model2025
Performs open-vocabulary promptable segmentation and tracking on images and videos, returning instance masks and unique IDs from short noun-phrase or exemplar prompts. Trained on a 4M-concept, 52M-mask dataset; uses a presence head and a decoupled detector–tracker design, with near real-time inference for multi-object video.
AI Train2026
Provides a one-command CLI to fine-tune and post-train LLMs, with layer streaming that lets an 8B model be fine-tuned on a 4 GB laptop GPU. Auto-configures quantization, LoRA adapters, batching and evaluation gates, and supports export and serving workflows.
AI Model2026
Performs one-shot, long-horizon OCR parsing of multi-page documents by using Reference Sliding Window Attention (R‑SWA) to keep the KV cache constant, enabling single-pass transcription of dozens of pages. Key features: constant KV cache, DeepEncoder visual compression, MoE-backed 3B model—suited for large-scale PDF/image parsing on GPU.
AI Infra2026
Streams routed experts from disk and treats storage, RAM and VRAM as a single inference hierarchy so MoE models (hundreds of billions to trillions of parameters) can run on consumer or heterogeneous hardware; single-file C engines with zero runtime deps and optional Vulkan/CUDA/Metal backends, speed governed by placement and disk I/O.
AI Dataset2026
Installation-oriented dataset that packages ComfyUI-ready files and instructions for running MiniMax H3 locally — includes pruned/INT8/BF16 checkpoints, matching Qwen3-VL text encoders, video/audio VAEs, and official ComfyUI workflow templates for joint audio+video generation.