Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
571.
▲
Hugging Face datasets and models for cybersecurity/sofwtare vulnerabilities
(huggingface.co)
7 points
cedricbonhomme
a year ago
1 comment
572.
▲
Addition is All You Need for Energy-efficient Language Models
(huggingface.co)
7 points
datapalo
2 years ago
1 comment
573.
▲
Hugging Face launches Agents 2.0
(huggingface.co)
7 points
aubanel
2 years ago
1 comment
574.
▲
OpenHermesPreferences: Dataset of ~1M AI preferences from teknium/OpenHermes-2.5
(huggingface.co)
7 points
kashifr
2 years ago
1 comment
575.
▲
Microsoft's Orca 7B may violate OpenAI's Terms of Use
(huggingface.co)
7 points
skadamat
3 years ago
1 comment
576.
▲
Stable Beluga 2 – Llama2 70B finetuned on an Orca style Dataset by Stability AI
(huggingface.co)
7 points
capableweb
3 years ago
1 comment
577.
▲
Databricks’ dolly-v2-12B, an instruction-following large language model
(huggingface.co)
7 points
srameshc
3 years ago
1 comment
578.
▲
Cerebras releases its own open source GPT models (Apache 2.0 License)
(huggingface.co)
7 points
armcat
3 years ago
1 comment
579.
▲
Nex N2 Pro: Frontier agentic performance at 400B
(huggingface.co)
7 points
himata4113
15 hours ago
discuss
580.
▲
The ultimate guide to RL environments: building and scaling them in the LLM era
(huggingface.co)
7 points
kashifr
a month ago
discuss
581.
▲
DeepSeek-V4
(huggingface.co)
7 points
meetpateltech
2 months ago
discuss
582.
▲
We OCR'ed 30k papers using Codex, open OCR models and Jobs
(huggingface.co)
7 points
speckx
2 months ago
discuss
583.
▲
Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI
(huggingface.co)
7 points
ibobev
3 months ago
discuss
584.
▲
Qwen 3.5: 9B, 4B, 2B, 0.8B
(huggingface.co)
7 points
tosh
3 months ago
discuss
585.
▲
Kimi-K2-Thinking: open weights LLM with frontier performance
(huggingface.co)
7 points
victormustar
7 months ago
discuss
586.
▲
DeepSeek-v3.1
(huggingface.co)
7 points
error404x
10 months ago
discuss
587.
▲
OpenAI/GPT-OSS-120B · Hugging Face
(huggingface.co)
7 points
synthwave
10 months ago
discuss
588.
▲
DeepSeek V3 0324 outpaces GPT 4.5 and Claude 3.7 in coding, other benchmarks
(huggingface.co)
7 points
xianshou
a year ago
discuss
589.
▲
Open-source DeepResearch – Freeing our search agents
(huggingface.co)
7 points
xd1936
a year ago
discuss
590.
▲
Llama 3.1 Nemotron 70B: Open model closing the gap with GPT-4o and Sonnet-3.5
(huggingface.co)
7 points
victormustar
2 years ago
discuss
591.
▲
Mini- Dust3r: A miniature version of dust3r running in a HuggingFace Space
(huggingface.co)
7 points
Tycho87
2 years ago
discuss
592.
▲
1B+ words corpus of original texts and experimental post-OCR correction output
(huggingface.co)
7 points
CharlesW
2 years ago
discuss
593.
▲
Grandmaster-Level Chess Without Search
(huggingface.co)
7 points
unstuck3958
2 years ago
discuss
594.
▲
Create a Web Interface for Your LLM in Python
(huggingface.co)
7 points
nevodavid
2 years ago
discuss
595.
▲
Show HN: DocQuery, an OSS tool for analyzing documents with LLMs
(huggingface.co)
7 points
ankrgyl
4 years ago
discuss
596.
▲
Show HN: State-of-the-Art Conversational AI
(convai.huggingface.co)
7 points
julien_c
7 years ago
discuss
597.
▲
Datadog scales time series foundation models to 2.5B parameters
(huggingface.co)
6 points
chrisdevs
a month ago
4 comments
598.
▲
Gemma 4 Uncensored (autoresearch results)
(huggingface.co)
6 points
adefa
2 months ago
4 comments
599.
▲
Show HN: A 0.3B model that redacts PII in all 24 EU languages offline
(huggingface.co)
6 points
mipo57
a month ago
3 comments
600.
▲
CodeFusion: A Pre-Trained Diffusion Model for Code Generation
(huggingface.co)
6 points
famouswaffles
3 years ago
3 comments
More