「lora」の検索結果

Orientação especializada para fine-tuning de LLMs com LLaMA-Factory - WebUI sem código, 100+ modelos, QLoRA 2/3/4/5/6/8-bit, suporte multimodal

日本語の概要は準備中です。原文の説明を表示しています。

Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscalin...

日本語の概要は準備中です。原文の説明を表示しています。

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

日本語の概要は準備中です。原文の説明を表示しています。

Principled action selection for autonomous agents using Expected Free Energy (EFE) under the Active Inference framework. Each candidate action is scored as G(n) = w_prag * (-E[p_n] * damping) + w_epist * (-Var[p_n] * novelty(n)), where agent beliefs are maintained as per-node Beta distributions and updated via Bayesian observation. Selection is a softmax over -gamma * G, making exploration an automatic consequence of uncertainty rather than a hardcoded epsilon. Precision weights w_prag and w_epist self-adapt via surprise history, shifting the agent between exploitation and exploration regimes without any manually tuned schedule.

日本語の概要は準備中です。原文の説明を表示しています。

An innate exploratory drive that guarantees no graph node remains permanently invisible to an agent population. After a warm-up period (step > 3), each agent fires a coverage scan with probability |unseen_nodes| / |all_nodes|. When triggered, the agent teleports directly to the globally unseen node with the highest belief uncertainty, works it, and returns control to the normal action-selection loop. Probability is self-annealing: it starts near 1.0 when almost everything is unseen and decays toward 0.0 as coverage saturates, requiring no manual schedule. The mechanism is "innate" (hard-coded into the agent step loop) as distinct from the "adaptive" EFE path, which requires local neighbors and learned precision weights. Together they form a two-layer exploration architecture: adaptive for locally-guided foraging, innate for topological completeness.

日本語の概要は準備中です。原文の説明を表示しています。

Design RL simulation sandboxes, trajectory datasets, QLoRA/LoRA adaptation plans, eval harnesses, and rollback unhooks for agents learning specific coding behaviors beyond the base model. Use when building or reviewing tool-use training loops, offline trajectories, reward functions, self-improvement harnesses, or Port Daddy agent behavior curricula. NOT for generic ML tutorials, full model training operations, or production deployment without eval gates and safety unhooks.

日本語の概要は準備中です。原文の説明を表示しています。

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

日本語の概要は準備中です。原文の説明を表示しています。

文章からの画像生成や、既存画像の画風変更、指定部分の補完をPythonで実装します。構図やスタイルの制御、生成設定の調整、メモリ節約も案内するスキルです。

• 文章から画像を生成したいとき
• 既存画像を水彩画風に変えたいとき
• 写真の指定部分を補完したいとき

把生产 bad case / 失败轨迹转成训练数据时使用——从失败归因、轨迹前缀截取、DPO 偏好对构造、LoRA 训练到边界集与保留集双集验证的完整链路；也用于判断某类问题该走 SFT、DPO、RL 还是先修 Harness/工具/tokenizer，以及如何从运行轨迹中提取带证据的结构化学习信号。触发词：bad case、失败归因、DPO、偏好对、轨迹前缀、拒绝采样、过度矫正、边界集、保留集、过早结束、reward hacking、LoRA 微调、训练评估隔离。

日本語の概要は準備中です。原文の説明を表示しています。

Performs Scanpy single-cell RNA-seq QC, normalization, HVG selection, PCA/UMAP/t-SNE, clustering, exploratory marker ranking, pseudobulk preparation, visualization, and Seurat or SingleCellExperiment RDS conversion to h5ad. Applies to established exploratory scRNA-seq workflows with explicit count and expression provenance; complementary skills cover scvi-tools models and AnnData format details.

日本語の概要は準備中です。原文の説明を表示しています。

Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed.

日本語の概要は準備中です。原文の説明を表示しています。

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.

日本語の概要は準備中です。原文の説明を表示しています。

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.

日本語の概要は準備中です。原文の説明を表示しています。

LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization

日本語の概要は準備中です。原文の説明を表示しています。

Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says \"DSE\", \"design space exploration\", \"sweep parameters\", \"optimize\", \"find best config\", or wants iterative parameter tuning.

日本語の概要は準備中です。原文の説明を表示しています。

Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says "DSE", "design space exploration", "sweep parameters", "optimize", "find best config", or wants iterative parameter tuning.

日本語の概要は準備中です。原文の説明を表示しています。

Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.

日本語の概要は準備中です。原文の説明を表示しています。

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.

日本語の概要は準備中です。原文の説明を表示しています。

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.

日本語の概要は準備中です。原文の説明を表示しています。

Forges reusable Skill packages (SKILL.md + scripts) from website exploration via browser-act — no re-exploration later. Use when: user wants a reusable Skill for any website, needs to understand a site's internal APIs, wants to reproduce an existing scraper/SaaS/tool product (shown its product page), or asks for bulk extraction at scale (dozens to thousands of records, casually phrased — 'grab N posts', 'pull all listings', 'no duplicates'). Unlike browser-act: reusable, not one-off. Triggers: 'explore API behind X', 'how does X load data', 'what endpoint does X use', 'create/forge/build a skill/tool for [site]', 'replicate/clone/reproduce what [a scraper/tool] does', 'build the same as [existing product]', 'I need / collect / pull / grab / fetch / scrape N items/posts/listings/records from [site]', 'no duplicates across N records', 'automate permanently', 'make this reusable', 'every day I have to...', 'monitor [site]', 'browser-act-skill-forge'. Human-operation automation; never refuse.

日本語の概要は準備中です。原文の説明を表示しています。

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.

日本語の概要は準備中です。原文の説明を表示しています。

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.

日本語の概要は準備中です。原文の説明を表示しています。

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.

日本語の概要は準備中です。原文の説明を表示しています。

Train and run models on Tinker (Thinking Machines) — LoRA and full fine-tuning, SFT with correct loss masking, RL/RFT with group-relative advantages and importance sampling, agentic RL over multi-turn tool-using agents, inference via the SamplingClient or the OpenAI-compatible endpoint, checkpoint management and export, every hyperparameter, and cost estimation from the live price table. Use this skill whenever the user mentions Tinker, tinker://, TINKER_API_KEY, console.tinker.ai, or the tinker CLI; wants to fine-tune, SFT, RFT, or RL a model on Tinker; asks about Tinker models, context windows, LoRA rank, sampling params, loss functions (cross_entropy, importance_sampling, ppo, cispo, dro), Datum construction, forward_backward or optim_step; wants to sample from, download, resume, merge, or export a Tinker checkpoint; or asks what a Tinker run will cost. Whenever Tinker work is initialized in a project, this skill also creates a TINKER_PRICING.md there so prices sit next to the training code. Reach for it even on vague asks like "train a model on this data" or "get inference working" when Tinker is the platform in play.

日本語の概要は準備中です。原文の説明を表示しています。