“accelerate”的搜索结果

Build image generation workflows in Python with Stable Diffusion and HuggingFace Diffusers. The guide covers text prompts, transforming existing images, replacing selected regions, controlling composition, applying learned styles, and adjusting memory use during generation.

中文简介正在准备中。当前显示英语简介。

• Generating images from text descriptions
• Changing the style of an existing image
• Replacing a selected region of an image

Compress large language models to 4-bit weights to reduce GPU memory use and accelerate inference. Covers loading compressed models, configuring quantization, and using Transformers or vLLM, with guidance on hardware requirements and backend choices.

中文简介正在准备中。当前显示英语简介。

• Running large models with limited GPU memory
• Compressing a model with domain-specific sample text
• Serving AWQ models with vLLM

Get guidance on adapting large language models with Axolotl. Covers YAML configuration files, LoRA and QLoRA methods for training fewer parameters, distributed training settings, dataset formats, and debugging training code.

中文简介正在准备中。当前显示英语简介。

• Write YAML settings for model fine-tuning
• Explore training with LoRA or QLoRA
• Configure training across multiple GPUs

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

Helps speed up LLM text generation by comparing methods that predict and verify multiple tokens at once. Covers draft model selection, Medusa prediction heads, Lookahead Decoding settings, and deployment examples for inference services.

中文简介正在准备中。当前显示英语简介。

• Reducing chatbot response latency
• Comparing methods for faster code generation
• Selecting a small draft model for a larger LLM

Train smaller language models using knowledge distillation, where a larger model supplies examples or prediction targets. This skill covers training losses, generated training data, parameter choices, and output comparisons to support model compression and specialized student models.

中文简介正在准备中。当前显示英语简介。

• Training a smaller model from a larger teacher
• Fine-tuning with teacher-generated responses
• Distilling domain knowledge into a specialized model

Helps configure and troubleshoot DeepSpeed for training large models across multiple devices. Covers memory optimization, parallel training, and DeepNVMe storage transfers, with examples for tuning data movement and configuring models that divide work among specialized components.

中文简介正在准备中。当前显示英语简介。

• Configuring distributed training for large models
• Tuning tensor transfers to NVMe storage
• Setting up models with specialized expert components

Evaluate code generation models with HumanEval, MBPP, and other benchmarks. Test generated programs, compare models across programming languages, and record pass@k scores, which estimate the chance that at least one of k solutions passes the tests.

中文简介正在准备中。当前显示英语简介。

• Comparing code generation models on shared benchmarks
• Measuring correctness across programming languages
• Evaluating models trained to follow instructions

Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.

中文简介正在准备中。当前显示英语简介。

• Clean web data for model training
• Remove exact and near duplicates from large text collections
• Redact personal information from training text

Manually drive a vehicle in CARLA, set a target speed, operate lights and doors, and adjust mass or drag. You can also inspect the command topics used to control the main vehicle through ROS 2.

中文简介正在准备中。当前显示英语简介。

• Manually test acceleration, steering, and braking
• Check vehicle lights and door operation
• Compare handling after changing mass or drag

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

Build image generation workflows in Python with Stable Diffusion and HuggingFace Diffusers. The guide covers text prompts, transforming existing images, replacing selected regions, controlling composition, applying learned styles, and adjusting memory use during generation.

中文简介正在准备中。当前显示英语简介。

• Generating images from text descriptions
• Changing the style of an existing image
• Replacing a selected region of an image

Reduce LLM generation delays with speculative decoding, which proposes tokens ahead of verification. This skill compares small draft models, Medusa, and Lookahead Decoding, with implementation examples, tuning guidance, and deployment using vLLM.

中文简介正在准备中。当前显示英语简介。

• Reducing response delays in chatbots
• Speeding up code generation
• Choosing a small model to draft candidate tokens

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

Evaluate code generation models with HumanEval, MBPP, and multilingual benchmarks. The skill guides test execution and model comparisons using pass@k, an estimate of whether at least one of k generated solutions passes the tests.

中文简介正在准备中。当前显示英语简介。

• Compare code generation models on shared benchmarks
• Measure code generation performance across languages
• Evaluate instruction-tuned coding models

Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.

中文简介正在准备中。当前显示英语简介。

• Clean web data for model training
• Remove exact and near duplicates from large text collections
• Redact personal information from training text

Guides LLM fine-tuning with Axolotl, from YAML configuration and dataset formats to distributed training across GPUs. Covers LoRA and QLoRA, methods that train on preferences, multimodal support, and troubleshooting using documentation references and code examples.

中文简介正在准备中。当前显示英语简介。

• Prepare YAML settings for LLM fine-tuning
• Explore LoRA, QLoRA, and preference training options
• Check dataset formats and input handling

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

Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.

中文简介正在准备中。当前显示英语简介。

• Train a model on instruction and response examples
• Align responses using preferred and rejected answer pairs
• Build a training pipeline using human feedback

Get guidance on adapting LLMs through additional training with LLaMA-Factory. The skill covers a visual interface requiring no code, LoRA and QLoRA training methods, and documentation-based help with implementation, features, and debugging.

中文简介正在准备中。当前显示英语简介。

• Learning additional training through a visual interface
• Exploring LoRA and QLoRA training methods
• Checking supported models and multimodal features

Implement and troubleshoot large-model training with DeepSpeed across multiple GPUs. The skill covers memory optimization, parallel training, and numerical precision choices, alongside examples for storage transfers and models that divide work among specialized components.

中文简介正在准备中。当前显示英语简介。

• Review settings for distributed model training
• Tune transfers between NVMe storage and tensors
• Configure training with specialized model components

Create a DESIGN.md guide for generating screens in Google Stitch. Define colors, typography, asymmetric layouts, component states, and motion with precise values and explicit restrictions, giving the agent consistent instructions for a specific visual style.

中文简介正在准备中。当前显示英语简介。

• Set shared design rules for Google Stitch screens
• Define asymmetric page layouts
• Document typography, colors, and interaction behavior

Assess WPA/WPA2 Personal Wi-Fi password strength through authentication data capture, file conversion, and offline password testing. Covers dictionary searches, pattern-based guesses, vendor default passwords, and capture quality checks.

中文简介正在准备中。当前显示英语简介。

• Assessing Wi-Fi password strength
• Checking captured authentication data
• Reviewing vendor default password patterns

Add, edit, or inspect animation on Figma elements through use_figma. Work with keyframes, existing animation styles, color changes, easing that controls how movement accelerates, and timeline duration, with video frame checks when needed.

中文简介正在准备中。当前显示英语简介。

• Adding position or color animation to Figma elements
• Adjusting easing and animation timing
• Applying or removing existing animation styles