“efficient inference”的搜索结果

Fit regression and time series models in Python, interpret coefficients, compare alternatives, and check model assumptions. Supports statistical diagnostics and forecasting, with confidence intervals and validation steps to assess uncertainty and predictive performance.

中文简介正在准备中。当前显示英语简介。

• Fit regression models and interpret coefficients
• Compare models for binary outcomes or counts
• Forecast time series with prediction intervals

Convert LLMs to GGUF and reduce model size through quantization, which stores weights at lower numerical precision. Prepare models for CPU or Apple Silicon inference, compare compression levels, and integrate them with local AI tools.

中文简介正在准备中。当前显示英语简介。

• Preparing an LLM for CPU-only use
• Running a local model on Apple Silicon
• Comparing model size and quality across quantization levels

Build and train Mixture of Experts models, which activate selected specialist networks for each input. Use DeepSpeed or HuggingFace workflows to configure routing, balance workloads, distribute experts across GPUs, and optimize inference.

中文简介正在准备中。当前显示英语简介。

• Designing MoE models for a limited compute budget
• Implementing Mixtral-style expert routing
• Adjusting expert workloads and training stability

Train Mixture of Experts models, which activate selected specialist networks for each input. The skill guides architecture, input routing, workload balancing, and GPU distribution using DeepSpeed or HuggingFace, with examples for training configuration and inference optimization.

中文简介正在准备中。当前显示英语简介。

• Designing a model that activates only selected expert networks
• Balancing workloads across expert networks
• Distributing experts across multiple GPUs

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.

中文简介正在准备中。当前显示英语简介。

• Build streaming text generation
• Process long documents in chunks
• Plan RWKV fine-tuning

Convert language models to GGUF and reduce their size through quantization, which stores model weights at lower precision. Guides cover compression choices, local inference on CPUs and Apple Silicon, and integration with tools such as Ollama.

中文简介正在准备中。当前显示英语简介。

• Running a language model on a CPU-only computer
• Choosing model compression for available memory
• Configuring Metal acceleration on Apple Silicon

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.

中文简介正在准备中。当前显示原文说明。

Reduce the memory needed to run large language models with GPTQ quantization, which stores model weights at lower precision. Covers loading compressed models, quantizing your own models, choosing execution backends, and connecting to memory-efficient fine-tuning.

中文简介正在准备中。当前显示英语简介。

• Run a language model within limited GPU memory
• Load a pre-quantized model for text generation
• Quantize and save your own trained model

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.

中文简介正在准备中。当前显示英语简介。

• Generate text with pretrained Mamba models
• Compare Mamba-1 and Mamba-2 configurations
• Benchmark generation speed against Transformers

Reduce GPU memory use by loading language models in 8-bit or 4-bit formats with bitsandbytes and HuggingFace Transformers. Includes configuration examples, QLoRA fine-tuning of compressed models, and optimizers that reduce memory needed during training.

中文简介正在准备中。当前显示英语简介。

• Load larger models within limited GPU memory
• Compare 8-bit and 4-bit model settings
• Fine-tune a model with QLoRA

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.

中文简介正在准备中。当前显示英语简介。

• Build streaming text generation
• Process long documents in chunks
• Compare memory needs with Transformers

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.

中文简介正在准备中。当前显示英语简介。

• Explore models for long sequences or streaming applications
• Generate text with pretrained Mamba models
• Compare Mamba-1 and Mamba-2 configurations

Helps reduce GPU memory use by loading large language models in 4-bit or 8-bit formats, a technique called quantization. Covers bitsandbytes configuration, memory checks, QLoRA fine-tuning, and training with memory-saving optimizers.

中文简介正在准备中。当前显示英语简介。

• Load a larger model within available GPU memory
• Compare 4-bit and 8-bit quantization settings
• Fine-tune a quantized model with QLoRA

Compress large language models to 4-bit weights to reduce GPU memory needs and accelerate text generation. Covers loading compressed models, converting your own models, choosing settings, and preparing memory-efficient fine-tuning with transformers and PEFT.

中文简介正在准备中。当前显示英语简介。

• Run language models with limited GPU memory
• Convert your own model to 4-bit weights
• Compare compression settings for quality and speed

Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.

中文简介正在准备中。当前显示原文说明。

Classical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem — dplyr + tidyr + haven + fixest + sandwich + lmtest + clubSandwich + AER + ivreg + did + bacondecomp + HonestDiD + eventstudyr + rdrobust + rddensity + Synth + gsynth + synthdid + MatchIt + WeightIt + cobalt + ebal + grf + DoubleML + mediation + marginaleffects + modelsummary + kableExtra + gt + ggplot2 + ggpubr + cowplot + binsreg. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a publication-ready output set with a multi-column regression table (M1→M6 progressive controls/FE) as the centerpiece, plus Table 1 (descriptives), mechanism / heterogeneity / robustness tables, and event-study + coefficient + trend figures. Covers the full 8-step R pipeline an applied economist runs on every paper — (1) data import & cleaning (read_dta/read_csv, naniar, janitor, validate-merges), (2) variable construction (mutate/across/winsorize/group_by + lag/lead with dplyr), (3) descriptive statistics & Table 1 (gtsummary, modelsummary::datasummary, tableone), (4) classical diagnostic tests (shapiro/jarque.bera.test/bptest/dwtest/bgtest/vif/adf.test/kpss.test/Hausman), (5) baseline modeling (fixest::feols, ivreg, did::att_gt, eventstudyr, sun_ab, did_imputation, synthdid, rdrobust, MatchIt, WeightIt, grf::causal_forest, DoubleML, mediation), (6) robustness battery (modelsummary stack, clubSandwich CRSE, fwildclusterboot, ri2, robomit Oster, bacondecomp, HonestDiD), (7) further analysis (interactions + marginaleffects, mediation::mediate, gsem via lavaan, dose-response splines, grf CATE), (8) publication-ready tables & figures (modelsummary, kableExtra, gt, stargazer, texreg, flextable to LaTeX/Word/HTML; ggplot2 + ggpubr + cowplot + binsreg + iplot for figures). **Also covers two parallel domain modes that share the same 8-step scaffolding** — **Mode A — Epidemiology / public health** (target-trial emulation, IPTW + g-formula + TMLE doubly-robust triplet via `WeightIt` / `gfoRmula` / `tmle` / `ltmle`, Mendelian randomization via `MendelianRandomization` / `TwoSampleMR` / `MRPRESSO`, KM / Cox / AFT / RMST survival via `survival` / `survminer` / `flexsurv`, E-value sensitivity via `EValue`, principal stratification — STROBE / TRIPOD reporting), and **Mode B — ML causal inference** (DML via `DoubleML`, S/T/X/R/DR meta-learners via `causalweight` / `grf`, causal forest via `grf::causal_forest`, BART/BCF via `bartCause` / `bcf`, matrix completion via `MCPanel`, CATE distribution + policy tree via `policytree`, off-policy evaluation, conformal causal via `conformalInference` / `cfcausal`, fairness audit via `fairmodels`, DAG learning via `pcalg` / `bnlearn` / LLM-assisted). Use when the user asks for a complete R empirical analysis, wants a tidyverse-style reproducible R script / Quarto workflow, prefers fixest over reghdfe, needs the R counterpart to StatsPAI / 00.1 / 00.2, or names a specific R step in isolation ("feols with cluster", "MatchIt nearest neighbor", "bacondecomp in R", "gtsummary table 1", "modelsummary to Word"). Mode A triggers on "target trial emulation R", "tmle ltmle", "MendelianRandomization", "TwoSampleMR", "MRPRESSO", "survival cox AFT", "STROBE R", "EValue R", "公共健康 R", "流行病学 R". Mode B triggers on "DoubleML R", "grf causal forest", "policytree", "bartCause bcf", "conformal causal R", "fairmodels", "pcalg NOTEARS", "因果机器学习 R".

中文简介正在准备中。当前显示原文说明。

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.

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。

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。

Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.

中文简介正在准备中。当前显示原文说明。

Helps extend how much text a language model can process at once. Covers choosing RoPE, YaRN, ALiBi, or position interpolation, implementing position information, fine-tuning on longer documents, and managing memory during inference.

中文简介正在准备中。当前显示英语简介。

• Extend an existing model to handle longer documents
• Compare context extension methods
• Implement position information in attention layers

Classical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid + did_imputation + eventstudyinteract + sdid + rdrobust + rddensity + synth + synth_runner + psmatch2 + teffects + ebalance + coefplot + esttab + asdoc + binscatter. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a publication-ready output set with a multi-column regression table (M1→M6 progressive controls/FE) as the centerpiece, plus Table 1 (descriptives), mechanism / heterogeneity / robustness tables, and event-study + coefficient + trend figures. Covers the full 8-step Stata pipeline an applied economist runs on every paper — (1) data import & cleaning (use/import, destring, misstable, duplicates, merge assert), (2) variable construction (gen/egen/winsor2/xtile/xtset with L./F./D.), (3) descriptive statistics & Table 1 (tabstat/balancetable/asdoc), (4) classical diagnostic tests (sktest/swilk/hettest/imtest/xtserial/xttest3/vif/dfuller/kpss/hausman/estat overid), (5) baseline modeling (reg/xtreg/reghdfe/ivreg2/ivregress/csdid/did_imputation/eventstudyinteract/sdid/rdrobust/synth/psmatch2/teffects/heckman/qreg/ppmlhdfe), (6) robustness battery (bacondecomp/honestdid/rwolf/ritest/wildbootstrap/oster), (7) further analysis (subgroup/triple-diff/interactions/medsem/marginsplot/binscatter by group), (8) publication-ready tables & figures (esttab/outreg2/estout/coefplot/marginsplot/rdplot/twoway combined). **Also covers two parallel domain modes that share the same 8-step scaffolding** — **Mode A — Epidemiology / public health** (target-trial emulation, IPTW + g-formula + TMLE doubly-robust triplet via `teffects ipw` / `teffects ipwra` / `teffects aipw` / `eltmle`, Mendelian randomization via `mrrobust` (IVW / Egger / weighted median) and `mregger` / `mrpresso`, KM / Cox / AFT / RMST survival via `sts` / `stcox` / `streg` / `strmst2`, E-value sensitivity via `evalue` (Linden-Mathur), principal stratification — STROBE / TRIPOD reporting), and **Mode B — ML causal inference** (DML via `ddml` / `pdslasso`, S/T/X/R/DR meta-learners via `crforest` and `ddml interactive`, causal forest via `crforest` / `cforest`, BART/BCF via `bart` / `bartCause`-style externals, CATE distribution + policy tree via `crforest`, off-policy evaluation, conformal causal externals, fairness audit, DAG learning via `pcalg` / external Python callouts). Use when the user asks for a complete Stata empirical analysis, wants a reproducible .do-file pipeline, needs a Stata counterpart to the Python StatsPAI / Full-empirical-analysis-skill, or names a specific Stata step in isolation ("run reghdfe with two-way clustering", "csdid event study", "winsor2 at 1%", "esttab to LaTeX", "coefplot with CI", "ivreg2 weak-IV test", "synth_runner placebos", "teffects psmatch balance check"). Mode A triggers on "target trial emulation Stata", "teffects ipw aipw", "eltmle", "mrrobust", "mregger weighted median", "stcox AFT survival", "strmst2", "evalue Stata", "STROBE Stata", "公共健康 Stata", "流行病学 Stata". Mode B triggers on "ddml Stata", "pdslasso", "crforest causal forest Stata", "policy tree Stata", "因果机器学习 Stata".

中文简介正在准备中。当前显示原文说明。

Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest + rdrobust + econml + causalml + matplotlib/seaborn. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a publication-ready output set with a multi-column regression table (M1→M6 progressive controls/FE) as the centerpiece, plus Table 1 (descriptives), mechanism / heterogeneity / robustness tables, and event-study + coefficient + trend figures. Covers the full 8-step pipeline an applied economist or quantitative social scientist runs on every paper — (1) data cleaning, (2) variable construction & transformation, (3) descriptive statistics & Table 1, (4) statistical diagnostic tests, (5) baseline empirical modeling, (6) robustness battery, (7) further analysis (mechanism, heterogeneity, mediation, moderation), (8) publication-ready tables & figures. **Also covers two parallel domain modes that share the same 8-step scaffolding** — **Mode A — Epidemiology / public health** (target-trial emulation via `zepid` / hand-rolled `pandas`, IPTW + g-formula + TMLE doubly-robust triplet via `zepid` / `econml` / `lifelines`, Mendelian randomization via `pymr` / `mrtool` (or `rpy2` → `MendelianRandomization`/`TwoSampleMR`), KM / AFT / Cox survival via `lifelines`, E-value sensitivity, principal stratification — STROBE / TRIPOD reporting), and **Mode B — ML causal inference** (DML via `econml.dml` / `doubleml`, S/T/X/R/DR meta-learners via `econml.metalearners` / `causalml`, causal forest via `econml.grf` / `causalml`, Dragonnet / TARNet / CEVAE neural causal via `causalml`, BCF via `pymc-bart` / `bcf-py`, matrix completion, CATE distribution + policy tree via `econml.policy` / `policytree-py`, off-policy evaluation, conformal causal via `mapie`, fairness audit via `fairlearn`, DAG learning via `causal-learn` / `cdt` / LLM-assisted). Prescribes which library to reach for at each step, shows the canonical code, and links to deeper `references/` files for variant-specific patterns. Use when the user asks for a **complete empirical analysis** in Python, wants to replicate an applied-economics paper from scratch, needs a reproducible workflow that is NOT opinionated on any single vertical package (contrast with StatsPAI), wants explicit control over every estimator and diagnostic, or asks "how do I write a full empirical pipeline in Python?". Also triggers when the user names a specific classical step in isolation — "winsorize at 1/99%", "run Breusch-Pagan", "build a Table 1 balance table", "do a placebo test", "event study plot", "mediation analysis" — and wants it wired into the broader pipeline. Mode A triggers on "target trial emulation", "IPTW", "TMLE", "Mendelian randomization", "STROBE", "公共健康", "流行病学". Mode B triggers on "DML", "double machine learning", "causal forest", "meta-learner", "Dragonnet", "BCF", "policy tree", "conformal causal", "fairness audit", "因果机器学习".

中文简介正在准备中。当前显示原文说明。

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

中文简介正在准备中。当前显示原文说明。