140 个 · 按相关度排序
Execute sophisticated Prompt Injection and Jailbreak techniques against Large Language Models (LLMs) to bypass safety filters, extract system prompts, and manipulate the AI's output to perform malicious or disallowed actions.
中文简介正在准备中。当前显示原文说明。
Monetization strategies for indie developers, solopreneurs, and small teams. Covers freemium models, SaaS pricing, sponsorships, donations, email list building, and passive income for developer tools, content sites, and educational apps. Activate on 'monetization', 'make money', 'pricing', 'freemium', 'SaaS', 'sponsorship', 'donations', 'passive income', 'indie hacker'. NOT for enterprise sales, B2B outbound, VC fundraising, or large-scale advertising (use enterprise/marketing skills).
中文简介正在准备中。当前显示原文说明。
Deep analysis of knowledge distillation techniques for compressing large models into smaller efficient ones
中文简介正在准备中。当前显示原文说明。
Quantify homologous recombination deficiency (HRD) from tumor copy number using the three genomic-scar metrics — loss of heterozygosity (LOH), large-scale state transitions (LST), and telomeric allelic imbalance (TAI) — with scarHRD, and via the whole-genome HRDetect and CHORD models. Covers the genomic instability score, the PARP-inhibitor clinical context, whole-genome-doubling correction, and the scar-versus-state distinction. Use when computing an HRD score for PARP-inhibitor eligibility, deriving LOH/LST/TAI scars from allele-specific copy number, deciding between scar-based and mutational-signature HRD methods, or interpreting an HRD result in a BRCA-reverted or low-purity tumor.
中文简介正在准备中。当前显示原文说明。
Framework RLHF de alta performance com aceleração Ray+vLLM. Use para treinamento PPO, GRPO, RLOO, DPO de modelos grandes (7B-70B+). Construído em Ray, vLLM, ZeRO-3. 2× mais rápido que DeepSpeedChat com arquitetura distribuída e compartilhamento de recursos GPU.
中文简介正在准备中。当前显示原文说明。
Deploy and use the Exasol Transformers Extension AI Functions for NLP inference inside Exasol with notebook-connector. Covers initialize_te_extension, model installation, activation SQL, validation, and safe use of large models.
中文简介正在准备中。当前显示原文说明。
B @ 3/4 bits models [2024-10-18] Open source community contributes Mistral Large Instruct 2407 (12
中文简介正在准备中。当前显示原文说明。
August 24, 2026 1 Introduction Reinforcement Learning (RL) has emerged as a highly effective approach for training Large Language Models (LLMs), yet i
中文简介正在准备中。当前显示原文说明。
To address this, we propose to recursively generate summaries/ memory using large language models (L
中文简介正在准备中。当前显示原文说明。
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.
中文简介正在准备中。当前显示原文说明。
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
中文简介正在准备中。当前显示原文说明。
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
中文简介正在准备中。当前显示原文说明。
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
中文简介正在准备中。当前显示原文说明。
Quantify homologous recombination deficiency (HRD) from tumor copy number using the three genomic-scar metrics — loss of heterozygosity (LOH), large-scale state transitions (LST), and telomeric allelic imbalance (TAI) — with scarHRD, and via the whole-genome HRDetect and CHORD models. Covers the genomic instability score, the PARP-inhibitor clinical context, whole-genome-doubling correction, and the scar-versus-state distinction. Use when computing an HRD score for PARP-inhibitor eligibility, deriving LOH/LST/TAI scars from allele-specific copy number, deciding between scar-based and mutational-signature HRD methods, or interpreting an HRD result in a BRCA-reverted or low-purity tumor.
中文简介正在准备中。当前显示原文说明。
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
中文简介正在准备中。当前显示原文说明。
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
中文简介正在准备中。当前显示原文说明。
Quantify homologous recombination deficiency (HRD) from tumor copy number using the three genomic-scar metrics — loss of heterozygosity (LOH), large-scale state transitions (LST), and telomeric allelic imbalance (TAI) — with scarHRD, and via the whole-genome HRDetect and CHORD models. Covers the genomic instability score, the PARP-inhibitor clinical context, whole-genome-doubling correction, and the scar-versus-state distinction. Use when computing an HRD score for PARP-inhibitor eligibility, deriving LOH/LST/TAI scars from allele-specific copy number, deciding between scar-based and mutational-signature HRD methods, or interpreting an HRD result in a BRCA-reverted or low-purity tumor.
中文简介正在准备中。当前显示原文说明。
Runs a session's fan-out — splits a large request into tiered, recoverable units, dispatches and reconciles them against the repo. Trigger when work needs many agents or spans many repos or files (rebuild, re-architect, sweep, migrate, 'do all of this'); when subagents would launch with no model or effort set; for the plan table (units, models, tokens, meters) before launch; to resume a unit that died or hit a usage limit; when units would share a repo; or say dispatchwright (plan, dispatch, resume, audit, refresh). Tiers come from its own table (scoutwright flags it stale); pacing, pacewright's; hooks, rigwright's; schedules, agentwright's.
中文简介正在准备中。当前显示原文说明。
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
中文简介正在准备中。当前显示原文说明。
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
中文简介正在准备中。当前显示原文说明。