Search: huggingface.co | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

601.

Create a Web Interface for Your LLM in Python

2 years ago

7 points

602.

Show HN: DocQuery, an OSS tool for analyzing documents with LLMs

4 years ago

7 points

603.

Show HN: State-of-the-Art Conversational AI

convai.huggingface.co

7 years ago

7 points

604.

Datadog scales time series foundation models to 2.5B parameters

a month ago

6 points

605.

Gemma 4 Uncensored (autoresearch results)

3 months ago

6 points

606.

Show HN: A 0.3B model that redacts PII in all 24 EU languages offline

a month ago

6 points

607.

CodeFusion: A Pre-Trained Diffusion Model for Code Generation

3 years ago

6 points

608.

Apple releases FastVLM and MobileCLIP2 on HF, real-time video captioning

10 months ago

6 points

609.

Show HN: We built a better reranker and open sourced it

10 months ago

6 points

610.

Nvidia STT Parakeet v3

10 months ago

6 points

611.

DeepSeek-R1 without CCP censorship

a year ago

6 points

612.

More Efficient Chain-of-Thought Reasoning Through Certainty Probing

a year ago

6 points

613.

Microsoft Phi 4 with R1 Reasoning

a year ago

6 points

614.

OpenChat 3.5: 7B model with comparable perf to ChatGPT

3 years ago

6 points

615.

Minimax M3 weights to be released on Friday

14 days ago

theanonymousone

6 points

616.

Arcee-AI Trinity-Large-Thinking

3 months ago

6 points

617.

Show HN: Nanbeige 4.1-3B running in the browser via WebGPU

4 months ago

6 points

618.

Unlocking On-Policy Distillation for Any Model Family

8 months ago

6 points

619.

Australian-made LLM beats OpenAI and Google at legal retrieval

8 months ago

6 points

620.

First 70B model released with all training epochs and data

9 months ago

6 points

621.

Qwen3-Next series represents our next-generation foundation models

9 months ago

6 points

622.

OpenAI deep research but it's open source

a year ago

6 points

623.

Hugging Face releases a barebones library for agents

a year ago

6 points

624.

New leaderboard drop: Judge Arena

2 years ago

6 points

625.

Phased Consistency Model

2 years ago

6 points

626.

3 years ago

6 points

627.

Generate Illusions with Stable Diffusion

3 years ago

angrypenguinpng

6 points

628.

Mann-E, an open source Equivalent of Midjourney reached its version 4.1.3

3 years ago

6 points

629.

Show HN: A 150M model that extracts verbatim evidence spans for RAG, no LLM call

15 days ago

6 points

630.

"Optimal Cognitive Core"- specialized 1.7B model for grounded question answering

22 days ago

6 points