Results for “huggingscience”

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page.

Publish and manage research papers on Hugging Face Hub, including creating paper pages, linking papers to models and datasets, claiming authorship, and generating professional markdown-based research articles.

Fetch dataset metadata, paginate rows, search text, apply filters, and download parquet URLs from the Hugging Face Dataset Viewer API.

Creates reusable command-line scripts and utilities for the Hugging Face API, enabling chaining, piping, and intermediate data processing.

Track and visualize ML training experiments with Trackio, including logging metrics, firing alerts, and retrieving data via CLI. Supports real-time dashboards, webhook alerts, and HF Space syncing.

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, and major labs. Supports HuggingFace, vLLM, APIs.

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, and major labs. Supports HuggingFace, vLLM, APIs.

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, and major labs. Supports HuggingFace, vLLM, APIs.

Operate Hugging Face Hub repositories, models, datasets, and Spaces via the hf CLI, including downloads, uploads, authentication, and compute jobs.

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

HuggingFace hf CLI: search/download/upload models, datasets.

Manage Hugging Face dataset Git repositories with Git Xet/LFS-compatible tracking, including setup, safe snapshot commits, push verification, binary rejection recovery, and README track-rule maintenance.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware, with backend selection between vLLM, Transformers, and accelerate.

Manage Hugging Face Hub resources: download/upload models, datasets, spaces; manage repos, buckets, collections, discussions, and cache; run SQL queries on datasets; authenticate and manage tokens.

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Search the Hugging Face Hub for llama.cpp-compatible GGUF models, select the right quantization, and run them locally with llama-cli or llama-server.

Create, deploy, and debug machine learning applications on Hugging Face Spaces using Gradio, Docker, or Static SDKs, with support for ZeroGPU and dedicated hardware.

Build ML demos on Hugging Face Spaces with ZeroGPU hardware, covering @spaces.GPU decorator usage, duration and quota tuning, process isolation, CUDA availability model, concurrency safety, and build constraints.

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs cloud infrastructure, with support for SFT, DPO, GRPO, and reward modeling, plus GGUF conversion for local deployment.

Queries Hugging Face benchmark leaderboards to find the best AI models for a task, filters by device constraints, and returns a ranked comparison table with scores.

Integrate a HuggingFace computer vision model into the NVIDIA TAO Toolkit ecosystem, covering the full pipeline from prerequisites to container testing.

Estimates the memory required to load Safetensors or GGUF model weights for inference from the Hugging Face Hub, using HTTP Range requests without downloading weights.

Selects the correct SageMaker serving container image URI for HuggingFace model deployments, prioritizing HuggingFace-curated Deep Learning Containers over generic alternatives.

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

HuggingFace hf CLI: search/download/upload models, datasets.

Filters and ranks trending Hugging Face models, datasets, and spaces by novelty and significance, providing a 'why notable' explanation for each pick.

Manage Hugging Face Hub resources via the `hf` CLI: download and upload models, datasets, and spaces; manage buckets, cache, collections, discussions, and inference endpoints; run SQL queries on datasets.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

llama.cpp local GGUF inference + HF Hub model discovery.

Build lightweight AI agents with HuggingFace Smolagents — use CodeAgent (writes Python to act) or ToolCallingAgent (JSON tool calls), add built-in or custom Tools, orchestrate multi-agent pipelines with ManagedAgent, and run locally or via HF Inference API.

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.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Filters the last 24 hours of Hugging Face Papers to surface one must-read paper with a structured brief covering the central claim, why it's worth an hour, where it might be wrong, and a time-budgeted read order.

Deploy Meta's LlamaGuard moderation model to filter LLM inputs and outputs across 6 safety categories using HuggingFace, vLLM, or FastAPI.