Results for “litgpt”

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

Create concise tldr summaries for GitHub Copilot customization files, MCP server documentation, or Copilot documentation from URLs or queries.

Scaffold, build, and refactor ChatGPT Apps SDK projects with a docs-first workflow, combining MCP servers and widget UIs.

Search scientific papers via the BGPT MCP server and retrieve structured experimental data — methods, results, conclusions, quality scores, and 25+ metadata fields per paper.

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server, returning 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions.

Train and experiment with a minimal GPT implementation in ~300 lines of PyTorch, from character-level Shakespeare to GPT-2 scale.

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.

Automates job search, auto-apply, resume generation, application tracking, salary intelligence, and recruiter outreach via the JobGPT MCP server.

Facilitates a read-only standup across git worktrees, branches, or PRs to compare changes and produce one consolidation plan.

Integrate Uniswap liquidity provisioning (LP) into applications via the LP REST API. Use when the user says "LP API", "liquidity provisioning API", "provide liquidity programmatically", "create LP position via API", "add liquidity via API", "increase liquidity", "decrease liquidity", "remove liquidity", "claim LP fees", "collect LP fees", "manage LP positions in code", or mentions building a backend, bot, or frontend that creates or manages Uniswap v2/v3/v4 liquidity positions through an API. Also use when debugging LP API calls (e.g. /lp/create, /lp/check_approval, /lp/increase, /lp/decrease, /lp/claim_fees), unexpected response fields, the approval or EIP-712 permit flow, or transaction-building errors for liquidity positions. For generating deep links to the Uniswap web app instead of calling the API, use the liquidity-planner skill; for using the Uniswap v4 SDK directly rather than the REST API, use the v4-sdk-integration skill.

Designs and automates identity governance lifecycle processes including joiner-mover-leaver workflows, role mining, access requests, periodic recertification, and orphaned account remediation using IGA platforms.

GPG (GNU Privacy Guard) encryption and signing reference. Covers key generation (Ed25519/RSA), export/import, keyservers, file encryption (symmetric + asymmetric), git commit signing, detached signatures, gpg-agent caching, SSH via GPG, and pass password manager.

GPG (GNU Privacy Guard) encryption and signing reference. Covers key generation (Ed25519/RSA), export/import, keyservers, file encryption (symmetric + asymmetric), git commit signing, detached signatures, gpg-agent caching, SSH via GPG, and pass password manager.

Guide pre-endoscopy management decisions for patients on GLP-1 receptor agonists (semaglutide, tirzepatide, liraglutide etc.), deciding whether to proceed, delay, or modify the approach based on GI symptoms, fasting status, and indication. Trigger when a clinician asks about GLP-1 RA and endoscopy, semaglutide before colonoscopy, Ozempic before procedure, or whether to hold a GLP-1 agonist before endoscopy.

Create tldr summaries for GitHub Copilot files (prompts, agents, instructions, collections), MCP servers, or documentation from URLs and queries.

Applies Brazil's LGPD framework to assess data processing legal bases, align with ANPD expectations, and classify personal data for privacy compliance.

Drafts institutional-quality Limited Partnership Agreements for PE/VC fund formation. Covers GP/LP terms, capital commitments, distribution waterfall, carried interest, LPAC governance, clawback, and tax provisions. Use when drafting LPA, fund formation agreement, limited partnership terms, or PE/VC fund documents.

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.

Use this skill for glTF/GLB assets, compression, optimization, transforms, texture sizing, browser delivery. Trigger when the task involves 3d web work related to Gltf Asset Pipeline, production implementation, audits, debugging, strategy, or validation.

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

Access ClinPGx pharmacogenomics data (the successor to PharmGKB) to query gene-drug interactions, CPIC/DPWG dosing guidelines, drug labels, and pharmacogene records. Use when interpreting pharmacogenes (CYP2D6, CYP2C19, TPMT, DPYD, SLCO1B1), looking up genotype-guided drug dosing, checking PGx drug-safety associations (e.g. HLA-B*57:01 and abacavir), or supporting precision medicine and clinical pharmacogenomics decisions. For star-allele definitions/frequencies see PharmVar; for germline/somatic variant pathogenicity see alterlab-clinvar. Part of the AlterLab Academic Skills suite.

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.

Generates a complete Custom GPT knowledge package from the current workspace project, producing 20 markdown documentation files plus optimized custom instructions for a strategic consultant.

Provides Git-like version control for ArcGIS web maps, exposing branch, commit, diff, push/pull, and map discovery as callable tools.

Model and solve LP, MILP, and QP problems using NVIDIA cuOpt's GPU-accelerated solver via Python, C/C++, or CLI interfaces.

Search and download specific files/folders from GitHub repositories directly from terminal using ghgrab, without full clone. Covers install, interactive browsing, release asset download, and automation-safe usage patterns.

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents GPT Image Edit's strengths (preservation language, multilingual in-image text editing, multi-reference up to 10 images, layout / typography precision), the schema, and when to route to Nano Banana Edit / Flux Kontext / GPT Image 2 t2i instead. Calls `runcomfy run openai/gpt-image-2/edit` through the local RunComfy CLI. Triggers on "gpt image edit", "gpt-image-edit", "chatgpt image edit", "edit with gpt image 2", or any explicit ask to edit with this model.

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.