Results for “transform”

Analyze recent screen activity via a local screenpipe daemon, detect repeated research workflows, and draft new skills or composition recipes for uncovered patterns.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on consumer GPUs.

Builds production RAG and semantic search systems with Qdrant, covering collection setup, vector indexing, filtered and hybrid search, and integration with LangChain and LlamaIndex.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining, covering SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Train AI models to be harmless through self-critique and AI feedback using a set of constitutional principles, without requiring human labels for harmful outputs.

Transforms fuzzy problems into structured briefs that AI agents can reason about, critique, and act upon, while evaluating how much of the problem can be automated.

Extends pandas for geospatial vector data analysis, including reading/writing shapefiles, GeoJSON, GeoPackage, and PostGIS, performing spatial joins, geometric operations, coordinate transformations, and creating static or interactive maps.

Build production RAG and semantic search systems with a high-performance vector database written in Rust, supporting hybrid search, filtering, and horizontal scaling.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends for deployment with vLLM or HuggingFace Transformers.

Selects the right Gemma model for a task, recommends deployment tooling (Gradio, Transformers.js, Vertex AI, MLX), and applies optimizations like MTP and QAT.

Build clinical deep-learning pipelines with PyHealth: load EHR, signal, and imaging datasets, define prediction tasks, instantiate models, train with the PyHealth Trainer, and compute clinical metrics.

Compress large language models using knowledge distillation from teacher to student models, covering temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Trains and analyzes Sparse Autoencoders (SAEs) with SAELens to decompose neural network activations into interpretable features, covering loading pre-trained SAEs, training custom ones, and feature steering.

Generates, edits, and transforms images via the Bria API, including text-to-image, background removal, product photography, and batch processing for e-commerce catalogs.

Discovers and uses scientific datasets, models, blog posts, and interactive demos from a curated catalog for AI/ML work in domains like biology, chemistry, physics, and genomics.

Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.

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.

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.

Compress large language models by 40-60% with minimal accuracy loss using one-shot pruning techniques like Wanda and SparseGPT, enabling faster inference and deployment on constrained hardware.

n8n workflow automation knowledge base. Provides n8n node information, node functionality details, workflow patterns, and configuration examples. Covers triggers, data transformation, data input/output, AI integration, covering 10 nodes. Keywords: n8n, workflow, automation, node, trigger, webhook, http request, database, ai agent.

Handle files and binary data in n8n workflows correctly, covering the $binary vs $json split, reading/writing binary, preserving binary across transforms, and the agent-tool binary boundary.

Generate image captions, answer visual questions, and perform image-text retrieval using BLIP-2's Q-Former architecture with frozen vision encoders and LLMs.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive agent", or mentions BDI ontology, mental state modeling, rational agency, or neuro-symbolic AI integration.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.

Quantize LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss using bitsandbytes. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.