Results for “loomio”

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA, including picking the right base pipeline, designing a tailored UI, and publishing the Space.

Builds input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs using NeMo Guardrails, Presidio, and Guardrails AI.

lemmaly — Algorithm-First Proof

Add programmable safety guardrails to LLM applications at runtime, including jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, and toxicity detection.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Enforces an algorithm-first discipline: state Big-O, data structure, and algorithm family before writing loops, queries, or recursion to catch O(n²), N+1, and brute-force defaults.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Manage Loom video recordings via the Loom API, including listing, retrieving details and transcripts, updating, deleting, and fetching analytics.

Manages Loom video libraries and analyzes engagement via the Loom API, covering video discovery, folder organization, sharing settings, and viewer analytics.

Maintain durable session memory across agent disconnects by writing structured checkpoints to the repo's session directory, enabling context recovery.

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

Algorithm-first discipline: state Big-O, data structure, and algorithm family BEFORE writing loops, queries, or recursion. Catches O(n^2), N+1, and brute-force defaults.

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.

When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for Ch...

Enforces an algorithm-first discipline: state Big-O, data structure, and algorithm family before writing loops, queries, or recursion, catching O(n^2), N+1, and brute-force defaults.

罗子君（都市剧虚构）认知与表达框架（压缩蒸馏）：全职太太 reboot、成长线与争议依赖 触发：我的前半生 等。虚构

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.

Algorithm-first discipline: state Big-O, data structure, and algorithm family BEFORE writing loops, queries, or recursion. Catches O(n^2), N+1, and brute-force defaults.

Embody the voice and methodology of Rumi to offer poetic, mystical guidance for emotional and spiritual struggles.

Algorithm-first discipline: state Big-O, data structure, and algorithm family BEFORE writing loops, queries, or recursion. Catches O(n^2), N+1, and brute-force defaults.

Detect abuse of legitimate Windows binaries (LOLBins) like certutil, regsvr32, mshta, and rundll32 using process telemetry, Sigma rules, and parent-child process analysis.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Algorithm-first discipline: state Big-O, data structure, and algorithm family BEFORE writing loops, queries, or recursion. Catches O(n^2), N+1, and brute-force defaults.

Solve single and multi-objective optimization problems using NSGA-II/III, MOEA/D, and other evolutionary algorithms with customizable operators, constraint handling, and benchmark problems.

LoRA: Low-Rank Adaptation of Large Language Models

GPU-accelerated data curation for LLM training, supporting text, image, video, and audio with fuzzy deduplication, quality filtering, semantic deduplication, PII redaction, and NSFW detection.

Solves single- and multi-objective optimization problems with NSGA-II/III, MOEA/D, and other evolutionary algorithms, including constraint handling, Pareto front analysis, and benchmark problems.

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.

Connects LLMs with user data for RAG applications, document Q&A, and knowledge retrieval using 300+ data connectors and vector indices.

Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.

Load expert mental models on-demand to enhance reasoning, with a library of modules across 15 categories and commands to manage a personal crew.

High-fidelity ASCII/Braille rendering via the Risomorphism-1911 pipeline — edge-aware downsampling, presets, quality gates, and eikon mirror workflows