Daniel Avila

Guide reinforcement learning, training models through rewards, with slime. Prepare data, configure Megatron-LM training and SGLang response generation, and set up asynchronous runs or custom multi-turn workflows for supported language models.

中文简介正在准备中。当前显示英语简介。

• Preparing reward-based training for GLM or Qwen models
• Overlapping response generation and training
• Training agents that use tools across multiple turns

Improve AI instructions with examples, clear output formats, and comparison tests. Use reusable templates and system prompts, which set ongoing behavior, to address inconsistent answers and investigate unexpected agent behavior.

中文简介正在准备中。当前显示英语简介。

• Making AI summaries more consistent
• Structuring information extracted from support tickets
• Creating reusable code review prompts

Plan and configure large language model training with OpenRLHF to better match human preferences. Covers training method selection, distributed GPU setup, inference acceleration with vLLM, and troubleshooting memory or training stability issues.

中文简介正在准备中。当前显示英语简介。

• Choosing a method for training models on human preferences
• Setting up PPO training with a reward model
• Configuring GRPO training without a critic model

Turn feature requirements into test plans, step-by-step manual tests, regression suites for checking existing features, and reproducible bug reports. The skill also supports comparing implemented interfaces with Figma designs and documenting visual differences.

中文简介正在准备中。当前显示英语简介。

• Plan tests for a new feature
• Write manual checkout test cases
• Organize regression checks before a release

Design and improve RAG systems, which retrieve documents to support language model answers. Explore meaningful document splitting, vector storage, combined keyword and semantic search, and relevance ranking while checking common causes of poor retrieval.

中文简介正在准备中。当前显示英语简介。

• Design a system that answers questions using documents
• Review document splitting when search misses relevant content
• Combine keyword search with search based on meaning

Build searches with Qdrant that find similar content and filter results by attributes. The skill covers document retrieval for AI answers, vector storage, memory optimization, and distributed deployment for larger collections.

中文简介正在准备中。当前显示英语简介。

• Building document retrieval for AI answers
• Combining similarity search with category or date filters
• Reducing memory use for large vector collections

Analyze Google Analytics traffic, visitor engagement, and conversions, such as purchases or goal completions. Compare periods, identify strong and weak pages or traffic sources, and receive prioritized recommendations with implementation guidance.

中文简介正在准备中。当前显示英语简介。

• Reviewing website performance over the last 30 days
• Identifying the main traffic sources
• Finding pages with high bounce rates

Design focused products built around AI APIs, with guidance on prompts, model selection, output validation, and user experience. Track usage and set cost limits to connect product behavior with operating costs and pricing decisions.

中文简介正在准备中。当前显示英语简介。

• Design an AI service for a specific task
• Create prompt templates and validate responses
• Track API costs and set usage limits

Turn a plain-language app request into a technology choice, project structure, and development plan. The skill coordinates specialist agents across interface, server, and database work, with templates for web, mobile, desktop, and other applications.

中文简介正在准备中。当前显示英语简介。

• Starting an app from a plain-language request
• Choosing technologies and a project structure
• Coordinating interface, server, and database development

Turn research code and experimental results into ML and AI paper drafts. The skill guides argument structure, reference verification, and conference formatting with LaTeX templates, helping researchers revise drafts and prepare submissions.

中文简介正在准备中。当前显示英语简介。

• Drafting a paper from research code and results
• Clarifying the main contribution and supporting evidence
• Finding and verifying references for related work

Use SAELens to train and analyze sparse autoencoders, which separate neural network activity into features that may represent recognizable concepts. Explore pretrained features, evaluate reconstruction quality, and investigate how individual features influence language model outputs.

中文简介正在准备中。当前显示英语简介。

• Exploring features with a pretrained SAE
• Training and evaluating a custom SAE
• Studying overlapping concepts in model activity

Get guidance on adapting LLMs with Unsloth, including implementation, API usage, and debugging. Covers LoRA and QLoRA, methods for adjusting models with fewer trainable parameters, with a focus on training speed and memory use.

中文简介正在准备中。当前显示英语简介。

• Learning how to fine-tune models with Unsloth
• Exploring LoRA and QLoRA for efficient training
• Implementing features using Unsloth APIs

Helps adapt LLMs to specific tasks with LLaMA-Factory, including training through a web interface and memory-saving methods such as QLoRA. Provides documentation references for learning features, implementing workflows, and investigating code problems.

中文简介正在准备中。当前显示英语简介。

• Exploring LLM fine-tuning through a web interface
• Checking LoRA and QLoRA training options
• Investigating LLaMA-Factory implementation problems

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

Evaluate language models with over 100 benchmark tests covering knowledge, math, coding, safety, and image understanding. Configure runs on Docker, Slurm computing clusters, or cloud infrastructure, compare models, and export results.

中文简介正在准备中。当前显示英语简介。

• Compare models using the same benchmark tests
• Run large evaluations on a Slurm cluster
• Evaluate safety and image understanding

Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.

中文简介正在准备中。当前显示英语简介。

• Compare models on standard knowledge and reasoning tests
• Track model performance across training checkpoints
• Organize evaluation results for research reports

Build image classification and search workflows by comparing images with text descriptions. Covers classification without additional training, similarity scoring, batch processing, and storing image representations in a vector database for retrieval.

中文简介正在准备中。当前显示英语简介。

• Classifying images without additional training
• Searching image collections with text descriptions
• Comparing images with candidate descriptions

Use W&B to record machine learning experiments, visualize training, and compare results. The skill also covers automated searches for training settings and version tracking for datasets and models, helping teams share experiments and trace their inputs.

中文简介正在准备中。当前显示英语简介。

• Logging training metrics and viewing progress in real time
• Comparing experiments with different training settings
• Searching automatically for better training settings

Build image captioning, visual question answering, and text-based image search with BLIP-2. The skill explains model selection, batch processing, and memory-saving settings, with Python examples for connecting image understanding to language models.

中文简介正在准备中。当前显示英语简介。

• Generating captions for multiple images
• Building a question-answering system for images
• Searching an image collection with text

Guides setup and operation of Lambda Labs GPU instances for machine learning training and inference. Covers SSH access, persistent storage, API automation, and multi-GPU or multi-node training, including how to retain checkpoints and terminate idle instances.

中文简介正在准备中。当前显示英语简介。

• Setting up a GPU instance for LLM fine-tuning
• Keeping datasets and checkpoints between sessions
• Automating instance launch and termination through the API

Generate music and sound effects from written descriptions with AudioCraft. Covers MusicGen and AudioGen, using reference melodies or musical styles, producing stereo audio, adjusting generation settings, and saving generated sounds as audio files.

中文简介正在准备中。当前显示英语简介。

• Generate music from a written description
• Create sound effects and environmental audio
• Generate music using a reference melody or style

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

Configure large language model pretraining with torchtitan across multiple GPUs. Covers ways to split training work, launch jobs on computing clusters, enable Float8 numerical processing, and save or resume training through distributed checkpoints.

中文简介正在准备中。当前显示英语简介。

• Pretraining Llama 3.1 8B on eight GPUs
• Configuring multi-node training with SLURM
• Enabling Float8 training on H100 GPUs

Use Phoenix to record execution traces, detailed records of an AI application's operations, and investigate problems. Evaluate answers on datasets, compare prompts and models, and set up monitoring through a self-hosted server.

中文简介正在准备中。当前显示英语简介。

• Investigate AI application problems using execution traces
• Evaluate answer quality across a test dataset
• Compare prompts and models through experiments