agentic-in/elephant-agent - 2페이지

modal

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

원문 언어: 영어

lm-evaluation-harness

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace,…

원문 언어: 영어

evaluation

Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.

원문 언어: 영어

weights-biases

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

원문 언어: 영어

hugging-face-hub

Guides model, dataset, and space workflows around Hugging Face Hub with explicit auth, artifact, and cache assumptions.

원문 언어: 영어

llama-cpp

Run LLM inference with llama.cpp on CPU, Apple Silicon, AMD/Intel GPUs, or NVIDIA — plus GGUF model conversion and quantization (2–8 bit with K-quants and imatrix). Covers CLI, Python bindings, OpenAI-compatible server, and Ollama/LM Studio integration. Use…

원문 언어: 영어

obliteratus

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules,…

원문 언어: 영어

outlines

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

원문 언어: 영어

inference

Guides model-serving and runtime-inference decisions across local, remote, and packaged deployment paths.

원문 언어: 영어

vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints,…

원문 언어: 영어

audiocraft

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.

원문 언어: 영어

clip

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning.…

원문 언어: 영어

segment-anything

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

원문 언어: 영어

stable-diffusion

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

원문 언어: 영어

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or…

원문 언어: 영어

dspy

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

원문 언어: 영어

axolotl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

원문 언어: 영어

peft

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…

원문 언어: 영어

pytorch-fsdp

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

원문 언어: 영어

training

Guides fine-tuning and post-training work with explicit data, objective, hardware, and rollback assumptions.

원문 언어: 영어

trl-fine-tuning

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…

원문 언어: 영어

unsloth

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

원문 언어: 영어

vector-databases

Guides retrieval-store design, indexing, and query behavior for embedding-backed systems without confusing storage with application truth.

원문 언어: 영어

obsidian

Work with vault-backed markdown notes in Obsidian, preserving links, filenames, and existing note structure.

원문 언어: 영어

google-workspace

Handle Google Docs, Sheets, Drive, and related Workspace tasks through the narrowest available API or browser workflow.

원문 언어: 영어

linear

Work with Linear issues, projects, and triage flows while preserving status semantics and ownership clarity.

원문 언어: 영어

nano-pdf

Extract, inspect, and summarize PDFs quickly with lightweight tooling before escalating to heavier OCR or layout workflows.

원문 언어: 영어

notion

Create, search, and update Notion pages or databases through the API or a narrow browser fallback when a Workspace lives in Notion.

원문 언어: 영어

ocr-and-documents

Recover text from scanned or image-heavy documents before attempting structured analysis or downstream writing tasks.

원문 언어: 영어

powerpoint

Build or revise presentation structure, slide copy, and export-ready material for PowerPoint-style decks.

원문 언어: 영어

telephony

Give Elephant Agent phone capabilities without core tool changes. Provision and persist a Twilio number, send and receive SMS/MMS, make direct calls, and place AI-driven outbound calls through Bland.ai or Vapi.

원문 언어: 영어

arxiv

Search, filter, and summarize arXiv papers with explicit titles, authors, dates, and paper links before drawing conclusions.

원문 언어: 영어

blogwatcher

Monitor blog or website updates, compare publish dates, and summarize deltas rather than repeating unchanged content.

원문 언어: 영어

llm-wiki

Build concise, cross-linked wiki-style summaries for models, papers, techniques, or labs when the user wants durable knowledge capture.

원문 언어: 영어

polymarket

Inspect prediction-market questions, prices, and resolution conditions carefully before summarizing or comparing market signals.

원문 언어: 영어

research-paper-writing

Draft research-style outlines, section structure, and evidence-backed prose for papers, whitepapers, or technical notes.

원문 언어: 영어

shell-execution

Keeps explicit shell work legible, bounded, and attached to the current workspace thread.

원문 언어: 영어

web-read

Keeps direct URL reading and text extraction available when a specific page matters more than search results.

원문 언어: 영어

workspace-search

Keeps local retrieval, file search, and nearby context gathering available in-session.

원문 언어: 영어

1password

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in, and reading/injecting secrets for commands.

원문 언어: 영어