7134 个 · 按相关度排序
Rebuild the vault dependency graph (_graph.md) via the deterministic generator script. /graph forces a full rebuild; /graph last (run after every /sync) rebuilds only if the vault changed; /graph [N] is treated as last. The generator reads the vault and writes _graph.md directly, so the file never streams through a model response.
中文简介正在准备中。当前显示原文说明。
Rebuild the vault dependency graph (_graph.md) via the deterministic generator script. $graph forces a full rebuild; $graph last (run after every $sync) rebuilds only if the vault changed; $graph [N] is treated as last. The generator reads the vault and writes _graph.md directly, so the file never streams through a model response.
中文简介正在准备中。当前显示原文说明。
Refresh the Key Metrics table in a thesis with current data from Financial Modeling Prep, with a Quartr standardized-statement tie-break for Revenue Growth / Gross Margin gaps (Step 4b-Q) and a scoped web-search fallback (Step 4b) when FMP has no data or resolved the wrong company. Use when user says "numbers", "refresh metrics", "update key metrics", or "refresh [TICKER]" with no other action implied. Surgical edit only — does NOT create research notes or propagate via /sync. Also flags (never auto-edits) stale price/valuation framing in the thesis Summary — see Step 10b.
中文简介正在准备中。当前显示原文说明。
Refresh the Key Metrics table in a thesis with current data from Financial Modeling Prep, with a scoped web-search fallback (Step 4b) when FMP has no data or resolved the wrong company. Use when user says "numbers", "refresh metrics", "update key metrics", or "refresh [TICKER]" with no other action implied. Surgical edit only — does NOT create research notes or propagate via $sync. Also flags (never auto-edits) stale price/valuation framing in the thesis Summary — see Step 10b.
中文简介正在准备中。当前显示原文说明。
Pull an earnings call transcript from Financial Modeling Prep, extract qualitative signal (management commentary deltas, hedging shifts, Q&A tone), and produce a thesis-delta-first Research note. Use when user says "transcript", "pull earnings call", "transcript diff", or "ingest [TICKER] earnings".
中文简介正在准备中。当前显示原文说明。
Extract typical annual GPP, annual evapotranspiration, mid-season LAI, mid-season root biomass, mid-season shoot biomass, median canopy height, maximum primary-root depth, Vcmax at 25oC, and Jmax at 25oC from EcoSIM h0 NetCDF output files. Use when asked to derive these EcoSIM output targets from a selected .ecosim.h0.*.nc file for model-output processing, trait checks, or benchmark summaries.
中文简介正在准备中。当前显示原文说明。
Extract study sites, observational variables, coordinates, climate-forcing sources, and cited data sources from ecosystem-modeling papers, PDFs, supplements, or article text, then plan or create EcoSIM simulation workflows and run folders for those sites. Use when Codex is asked to read a paper for EcoSIM feasibility, including requests phrased as "read paper for ecosim feasibility"; read a paper for sites/data availability; reproduce a published site simulation in EcoSIM; compare EcoSIM outputs to paper observations; or convert paper-derived AmeriFlux, FLUXNET, US NLDAS-domain, non-US ERA5, crop, peatland, forest, grassland, wetland, or unmanaged field-site information into EcoSIM inputs and runnable cases.
中文简介正在准备中。当前显示原文说明。
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
中文简介正在准备中。当前显示原文说明。
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
中文简介正在准备中。当前显示原文说明。
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
中文简介正在准备中。当前显示原文说明。
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
中文简介正在准备中。当前显示原文说明。
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.
中文简介正在准备中。当前显示原文说明。
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform
中文简介正在准备中。当前显示原文说明。
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
中文简介正在准备中。当前显示原文说明。
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
中文简介正在准备中。当前显示原文说明。
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
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。
Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.
中文简介正在准备中。当前显示原文说明。
Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.
中文简介正在准备中。当前显示原文说明。
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
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。
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
中文简介正在准备中。当前显示原文说明。
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
中文简介正在准备中。当前显示原文说明。
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
中文简介正在准备中。当前显示原文说明。