社区博客与文章

Community Articles

How we OCR'ed 30,000 papers using Codex, open OCR models and Jobs

NEO-unify: Building Native Multimodal Unified Models End to End

"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"

When Speech AI Meets the Long Tail of Languages: Inside the VAANI Dataset

Nucleus-Image: Scaling Text-to-Image with Sparse Mixture of Experts

Stop benchmarking inference providers

Darwin-TTS: We Gave a TTS Model 3% of an LLM's Brain — It Started Showing Emotion

Uncensor any LLM with abliteration

KV Caching Explained: Optimizing Transformer Inference Efficiency

Mastering Tensor Dimensions in Transformers

Using OCR models with llama.cpp

Releasing LiteCoder-Terminal-SFT

NVIDIA Isaac GR00T N1.7: Open Reasoning VLA Model for Humanoid Robots

easyaligner: Forced alignment of text and audio, made easy

Code a simple RAG from scratch

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons

ALTK‑Evolve: On‑the‑Job Learning for AI Agents

Holo3: Breaking the Computer Use Frontier

nanoVLM: 最简洁、最轻量的纯 PyTorch 视觉-语言模型训练代码库

+3

2025年5月21日

vlmvisionmultimodal

视觉语言模型 (更好、更快、更强)

+1

2025年5月12日

vlmmultimodalvideo

SmolVLM2：让视频理解能力触手可及

+3

2025年2月20日

AI艺术工具通讯 - 第1期

2025年1月31日

multimodalvlmvision

SmolVLM 越变越小 —— 全新 250M 和 500M 模型正式发布！

2025年1月23日

人工智能代理已经到来，接下来呢？

2025年1月13日

multimodalgemmaLLM

欢迎 PaliGemma 2 – 来自 Google 的新视觉语言模型

2024年12月5日

policyguideethics

开源开发者指南：欧盟《人工智能法案》解读

2024年12月2日

researchmultimodaltutorial

设计位置编码

2024年11月25日

researchnlpopen-source

LayerSkip：使用自推测解码加速大模型推理

2024年11月20日

dedupestoragecontent defined chunking

从文件到块：提高 Hugging Face 存储效率

2024年11月20日

communityresearchdatasets

在 Hugging Face Hub 分享你的开源数据集

2024年11月12日

announcementopen-sourcecommunity

Hugging Face 与 PyCharm 深度集成：轻松引入丰富的 AI 模型

2024年11月5日

researchnlpopen-source

通用辅助生成：使用任意辅助模型加速解码

+4

2024年10月29日

Community Articles

NEW Articles from Team or Enterprise organizations will get promoted to the main section.

How we OCR'ed 30,000 papers using Codex, open OCR models and Jobs

NEO-unify: Building Native Multimodal Unified Models End to End

"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"

When Speech AI Meets the Long Tail of Languages: Inside the VAANI Dataset

Nucleus-Image: Scaling Text-to-Image with Sparse Mixture of Experts

Stop benchmarking inference providers

Darwin-TTS: We Gave a TTS Model 3% of an LLM's Brain — It Started Showing Emotion

Uncensor any LLM with abliteration

KV Caching Explained: Optimizing Transformer Inference Efficiency

Mastering Tensor Dimensions in Transformers

Using OCR models with llama.cpp

Releasing LiteCoder-Terminal-SFT

NVIDIA Isaac GR00T N1.7: Open Reasoning VLA Model for Humanoid Robots

easyaligner: Forced alignment of text and audio, made easy

Code a simple RAG from scratch

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons

ALTK‑Evolve: On‑the‑Job Learning for AI Agents

Holo3: Breaking the Computer Use Frontier

View all articles