Search: huggingface.co | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

571.

Show HN: Step up your Midjourney AI images with this prompt autocomplete

4 years ago

7 points

572.

Carbon: Autoregressive Genomic Foundation Model

a month ago

7 points

573.

Transformers v5 Is Out

7 months ago

unofficialmerve

7 points

574.

DeepSeek-v3.2-Exp

9 months ago

7 points

575.

Holo1.5: Foundational Models for Computer Use Agents

9 months ago

7 points

576.

a year ago

7 points

577.

ByteDance/Dolphin on HuggingFace

a year ago

7 points

578.

Hugging Face datasets and models for cybersecurity/sofwtare vulnerabilities

a year ago

7 points

579.

Addition is All You Need for Energy-efficient Language Models

2 years ago

7 points

580.

Hugging Face launches Agents 2.0

2 years ago

7 points

581.

OpenHermesPreferences: Dataset of ~1M AI preferences from teknium/OpenHermes-2.5

2 years ago

7 points

582.

Microsoft's Orca 7B may violate OpenAI's Terms of Use

3 years ago

7 points

583.

Stable Beluga 2 – Llama2 70B finetuned on an Orca style Dataset by Stability AI

3 years ago

7 points

584.

Databricks’ dolly-v2-12B, an instruction-following large language model

3 years ago

7 points

585.

Cerebras releases its own open source GPT models (Apache 2.0 License)

3 years ago

7 points

586.

Nex N2 Pro: Frontier agentic performance at 400B

17 days ago

7 points

587.

The ultimate guide to RL environments: building and scaling them in the LLM era

2 months ago

7 points

588.

2 months ago

7 points

589.

We OCR'ed 30k papers using Codex, open OCR models and Jobs

2 months ago

7 points

590.

Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI

3 months ago

7 points

591.

Qwen 3.5: 9B, 4B, 2B, 0.8B

4 months ago

7 points

592.

Kimi-K2-Thinking: open weights LLM with frontier performance

8 months ago

7 points

593.

10 months ago

7 points

594.

OpenAI/GPT-OSS-120B · Hugging Face

a year ago

7 points

595.

DeepSeek V3 0324 outpaces GPT 4.5 and Claude 3.7 in coding, other benchmarks

a year ago

7 points

596.

Open-source DeepResearch – Freeing our search agents

a year ago

7 points

597.

Llama 3.1 Nemotron 70B: Open model closing the gap with GPT-4o and Sonnet-3.5

2 years ago

7 points

598.

Mini- Dust3r: A miniature version of dust3r running in a HuggingFace Space

2 years ago

7 points

599.

1B+ words corpus of original texts and experimental post-OCR correction output

2 years ago

7 points

600.

Grandmaster-Level Chess Without Search

2 years ago

7 points