Blog, Articles, and discussions

HuggingFace, IISc partner to supercharge model building on India's diverse languages

By February 27, 2025 • 17

Community Articles

🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?

Open-Source Handwritten Signature Detection Model

Digest of models based on YandexGPT 5 Lite

DeepSearch Using Visual RAG in Agentic Frameworks 🔎

and 1 other •

Open R1: Update #3

and 9 others •

Uncensor any LLM with abliteration

Deploy Multimodal Models from Hugging Face to FriendliAI with Ease

and 2 others •

Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques

and 8 others •

makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch

ColPali: Efficient Document Retrieval with Vision Language Models 👀

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

Gradio’s Dataframe has been upgraded! 🎨

The Large Language Model Course

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

What is Qwen-Agent framework? Inside the Qwen family

and 1 other •

KV Caching Explained: Optimizing Transformer Inference Efficiency

What is test-time compute and how to scale it?

and 1 other •

🌁#92: Fight for Developers and the Year of Orchestration

LLM Routing for Batched Instructions

PangolinGuard: Fine-Tuning ModernBERT as a Lightweight Approach to AI Guardrails

Boost Wav2Vec2 with n-gram LM in 🤗 Transformers

By January 12, 2022 • 9

Perceiver IO: a scalable, fully-attentional model that works on any modality

By December 15, 2021 • 6

Fine-tuning XLS-R for Multi-Lingual ASR with 🤗 Transformers

By November 15, 2021 • 24

Fine-Tune Wav2Vec2 for English ASR with 🤗 Transformers

By March 12, 2021 • 20

Community Articles

🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?

Open-Source Handwritten Signature Detection Model

Digest of models based on YandexGPT 5 Lite

DeepSearch Using Visual RAG in Agentic Frameworks 🔎

and 1 other •

Open R1: Update #3

and 9 others •

Uncensor any LLM with abliteration

Deploy Multimodal Models from Hugging Face to FriendliAI with Ease

and 2 others •

Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques

and 8 others •

makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch

ColPali: Efficient Document Retrieval with Vision Language Models 👀

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

Gradio’s Dataframe has been upgraded! 🎨

The Large Language Model Course

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

What is Qwen-Agent framework? Inside the Qwen family

and 1 other •

KV Caching Explained: Optimizing Transformer Inference Efficiency

What is test-time compute and how to scale it?

and 1 other •

🌁#92: Fight for Developers and the Year of Orchestration

LLM Routing for Batched Instructions

PangolinGuard: Fine-Tuning ModernBERT as a Lightweight Approach to AI Guardrails

View all