11 skills · sorted by relevance
Implement Mamba, a model architecture that processes sequences through an internal state with computation scaling linearly with input length. Covers pretrained text generation, Mamba-1 and Mamba-2 configuration, speed comparisons with Transformers, and GPU memory troubleshooting.
Guides the use of RWKV, a language model architecture that carries information forward in a compact state. Covers streaming text generation, long document processing, fine-tuning, and memory comparisons with Transformers.
Build and evaluate Mamba models for long sequences using state-space models, which summarize past inputs in an internal state. Covers setup, pretrained text generation, differences between Mamba-1 and Mamba-2, and speed comparisons with Transformers.
Guides you through setting up RWKV, generating text, processing long documents in chunks, and fine-tuning models. Explains how to carry context between steps and compare memory use with Transformer models.
Híbrido RNN+Transformer com inferência O(n). Tempo linear, contexto infinito, sem cache KV. Treina como GPT (paralelo), infere como RNN (sequencial). Projeto Linux Foundation AI. Produção em Windows, Office, NeMo. RWKV-7 (março de 2025). Modelos até 14B parâmetros.
The English summary is being prepared. Showing the original description.
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
The English summary is being prepared. Showing the original description.
Design and build an OpenMAIC lesson series using a spiral curriculum: core ideas return with deeper explanations, new representations, and unfamiliar applications. It maps conceptual growth across lessons and checks that revisits add understanding.
Algorithms and data structures from first principles through advanced analysis. Covers sorting (bubble, insertion, selection, merge, quick, heap, radix), searching (linear, binary, BFS, DFS, Dijkstra, A*), fundamental data structures (arrays, linked lists, stacks, queues, hash tables, trees, heaps, graphs, tries), complexity analysis (Big-O, Big-Omega, Big-Theta, amortized), recurrence relations, and algorithm design paradigms (divide-and-conquer, greedy, dynamic programming, backtracking). Use when analyzing, selecting, implementing, or comparing algorithms and data structures.
The English summary is being prepared. Showing the original description.
ABD quorum-based linearizable registers for distributed storage — the canonical crash-tolerant read/write protocol with precise RTT and message complexity.
The English summary is being prepared. Showing the original description.
The intelligence layer of WinDAGs. Decomposes natural language tasks into Hierarchical Task DAGs (HTDAGs), matches subtasks to skills, executes waves in parallel, and dynamically expands nodes when complexity exceeds executor capability. Use for 'orchestrate', 'execute DAG', 'parallel agents', 'decompose task', 'coordinate skills'. NOT for single-skill tasks or simple linear workflows.
The English summary is being prepared. Showing the original description.
Modelo de espaço de estados com complexidade O(n) versus O(n²) dos Transformers. Inferência 5× mais rápida, sequências de milhão de tokens, sem cache KV. SSM seletivo com design aware de hardware. Mamba-1 (d_state=16) e Mamba-2 (d_state=128, multi-head). Modelos 130M-2.8B no HuggingFace.
The English summary is being prepared. Showing the original description.