Hugging Face H4

company

https://github.com/huggingface/alignment-handbook

AI & ML interests

Aligning LLMs to be helpful, honest, harmless, and huggy (H4)

Recent Activity

AdithyaSK updated a Space 7 days ago

HuggingFaceH4/harbor-visualiser

clefourrier authored a paper 2 months ago

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

sayakpaul authored a paper 3 months ago

Fine-Grained Perturbation Guidance via Attention Head Selection

View all activity

Organization Card

Community About org cards

Hello world!

We're the Hugging Face H4 team, focused on aligning language models to be helpful, honest, harmless, and huggy 🤗.

Collections 10

View 10 collections

spaces 18

Zephyr Chat

Chat with an AI model

Harbor Visualiser

Browse Harbor task specs from HF, GitHub, or local

Unlocking On-Policy Distillation for Any Model Family

Visualize on-policy distillation for any model family

Falcon-Chat

Interact with Falcon-Chat for personalized conversations

Human & GPT-4 Evaluation of LLMs Leaderboard

Scaling test-time compute

Learn to boost LLM math solving with test-time compute scaling

models 36

HuggingFaceH4/Qwen3-4B-Thinking-2507-SFT-tr5

HuggingFaceH4/KD-Tinker

Text Generation • 8B • Updated Feb 3 • 18

HuggingFaceH4/SmolLM3-3B-QAT-Baseline-Q

Text Generation • Updated Sep 3, 2025 • 19

HuggingFaceH4/Qwen2.5-1.5B-Instruct-gkd

2B • Updated Jun 18, 2025 • 16 • 2

HuggingFaceH4/Qwen2.5-Math-7B-Instruct-PRM-0.2

Token Classification • 7B • Updated Jan 9, 2025 • 19

HuggingFaceH4/Qwen2.5-Math-1.5B-Instruct-PRM-0.2

Token Classification • 2B • Updated Jan 9, 2025 • 31

HuggingFaceH4/zephyr-7b-alpha

7B • Updated Oct 16, 2024 • 4.4k • 1.12k

HuggingFaceH4/zephyr-7b-beta

Text Generation • 7B • Updated Oct 16, 2024 • 182k • 1.84k

HuggingFaceH4/mistral-7b-sft-beta

Text Generation • Updated Sep 24, 2024 • 2.69k • • 25

HuggingFaceH4/sft-llava-1.5-7b-hf

Updated Jul 26, 2024 • 4

datasets 90

HuggingFaceH4/MATH-500

Viewer • Updated Dec 15, 2025 • 500 • 176k • 310

HuggingFaceH4/Polaris-Dataset-53K

Viewer • Updated Nov 10, 2025 • 53.3k • 59 • 1

HuggingFaceH4/OpenR1-Math-220k-default-verified

Viewer • Updated Sep 23, 2025 • 52.7k • 342 • 2

HuggingFaceH4/grok-conversation-harmless

Updated Aug 26, 2025 • 273 • 29

HuggingFaceH4/tau2-bench-data

Preview • Updated Aug 19, 2025 • 502

HuggingFaceH4/Multilingual-Thinking

Viewer • Updated Aug 7, 2025 • 1k • 10.4k • 115

HuggingFaceH4/numina_60k_math_verify_correct_2_4gens_with_rm_scores

Viewer • Updated Feb 5, 2025 • 14.8k • 51 • 1

HuggingFaceH4/s1k_r1_math_verify

Viewer • Updated Feb 5, 2025 • 1k • 26 • 1

HuggingFaceH4/MATH

Viewer • Updated Jan 28, 2025 • 13.8k • 2.49k • 9

HuggingFaceH4/aime_2024

Viewer • Updated Jan 26, 2025 • 30 • 59.4k • 63

View 90 datasets